update jupyter-book
This commit is contained in:
Morten Hjorth-Jensen
@@ -6,11 +6,11 @@ edge [fontname="helvetica"] ;
|
||||
0 -> 1 [labeldistance=2.5, labelangle=45, headlabel="True"] ;
|
||||
2 [label="worst concave points <= 0.135\ngini = 0.031\nsamples = 253\nvalue = [[249, 4]\n[4, 249]]", fillcolor="#e78946"] ;
|
||||
1 -> 2 ;
|
||||
3 [label="radius error <= 0.643\ngini = 0.008\nsamples = 242\nvalue = [[241, 1]\n[1, 241]]", fillcolor="#e5833c"] ;
|
||||
3 [label="area error <= 48.975\ngini = 0.008\nsamples = 242\nvalue = [[241, 1]\n[1, 241]]", fillcolor="#e5833c"] ;
|
||||
2 -> 3 ;
|
||||
4 [label="gini = 0.0\nsamples = 239\nvalue = [[239, 0]\n[0, 239]]", fillcolor="#e58139"] ;
|
||||
3 -> 4 ;
|
||||
5 [label="perimeter error <= 4.249\ngini = 0.444\nsamples = 3\nvalue = [[2, 1]\n[1, 2]]", fillcolor="#fdf6f0"] ;
|
||||
5 [label="radius error <= 0.688\ngini = 0.444\nsamples = 3\nvalue = [[2, 1]\n[1, 2]]", fillcolor="#fdf6f0"] ;
|
||||
3 -> 5 ;
|
||||
6 [label="gini = 0.0\nsamples = 1\nvalue = [[0, 1]\n[1, 0]]", fillcolor="#e58139"] ;
|
||||
5 -> 6 ;
|
||||
@@ -22,7 +22,7 @@ edge [fontname="helvetica"] ;
|
||||
8 -> 9 ;
|
||||
10 [label="gini = 0.0\nsamples = 3\nvalue = [[0, 3]\n[3, 0]]", fillcolor="#e58139"] ;
|
||||
8 -> 10 ;
|
||||
11 [label="mean texture <= 16.22\ngini = 0.278\nsamples = 6\nvalue = [[1, 5]\n[5, 1]]", fillcolor="#f4caac"] ;
|
||||
11 [label="worst texture <= 24.785\ngini = 0.278\nsamples = 6\nvalue = [[1, 5]\n[5, 1]]", fillcolor="#f4caac"] ;
|
||||
1 -> 11 ;
|
||||
12 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139"] ;
|
||||
11 -> 12 ;
|
||||
@@ -30,11 +30,11 @@ edge [fontname="helvetica"] ;
|
||||
11 -> 13 ;
|
||||
14 [label="worst texture <= 20.645\ngini = 0.202\nsamples = 167\nvalue = [[19, 148]\n[148, 19]]", fillcolor="#f0b68c"] ;
|
||||
0 -> 14 [labeldistance=2.5, labelangle=-45, headlabel="False"] ;
|
||||
15 [label="worst concavity <= 0.318\ngini = 0.375\nsamples = 16\nvalue = [[12, 4]\n[4, 12]]", fillcolor="#f9e3d4"] ;
|
||||
15 [label="worst radius <= 17.74\ngini = 0.375\nsamples = 16\nvalue = [[12, 4]\n[4, 12]]", fillcolor="#f9e3d4"] ;
|
||||
14 -> 15 ;
|
||||
16 [label="gini = 0.0\nsamples = 11\nvalue = [[11, 0]\n[0, 11]]", fillcolor="#e58139"] ;
|
||||
15 -> 16 ;
|
||||
17 [label="mean perimeter <= 98.115\ngini = 0.32\nsamples = 5\nvalue = [[1, 4]\n[4, 1]]", fillcolor="#f6d5bd"] ;
|
||||
17 [label="worst compactness <= 0.126\ngini = 0.32\nsamples = 5\nvalue = [[1, 4]\n[4, 1]]", fillcolor="#f6d5bd"] ;
|
||||
15 -> 17 ;
|
||||
18 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139"] ;
|
||||
17 -> 18 ;
|
||||
@@ -42,13 +42,13 @@ edge [fontname="helvetica"] ;
|
||||
17 -> 19 ;
|
||||
20 [label="mean concave points <= 0.049\ngini = 0.088\nsamples = 151\nvalue = [[7, 144]\n[144, 7]]", fillcolor="#ea985d"] ;
|
||||
14 -> 20 ;
|
||||
21 [label="concave points error <= 0.01\ngini = 0.48\nsamples = 15\nvalue = [[6, 9]\n[9, 6]]", fillcolor="#ffffff"] ;
|
||||
21 [label="compactness error <= 0.016\ngini = 0.48\nsamples = 15\nvalue = [[6, 9]\n[9, 6]]", fillcolor="#ffffff"] ;
|
||||
20 -> 21 ;
|
||||
22 [label="gini = 0.0\nsamples = 9\nvalue = [[0, 9]\n[9, 0]]", fillcolor="#e58139"] ;
|
||||
21 -> 22 ;
|
||||
23 [label="gini = 0.0\nsamples = 6\nvalue = [[6, 0]\n[0, 6]]", fillcolor="#e58139"] ;
|
||||
21 -> 23 ;
|
||||
24 [label="mean smoothness <= 0.079\ngini = 0.015\nsamples = 136\nvalue = [[1, 135]\n[135, 1]]", fillcolor="#e6853f"] ;
|
||||
24 [label="worst smoothness <= 0.096\ngini = 0.015\nsamples = 136\nvalue = [[1, 135]\n[135, 1]]", fillcolor="#e6853f"] ;
|
||||
20 -> 24 ;
|
||||
25 [label="gini = 0.0\nsamples = 1\nvalue = [[1, 0]\n[0, 1]]", fillcolor="#e58139"] ;
|
||||
24 -> 25 ;
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 242 KiB After Width: | Height: | Size: 244 KiB |
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
Before Width: | Height: | Size: 14 KiB After Width: | Height: | Size: 14 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 19 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 23 KiB After Width: | Height: | Size: 25 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 18 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 29 KiB After Width: | Height: | Size: 28 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 29 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 48 KiB After Width: | Height: | Size: 50 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 39 KiB After Width: | Height: | Size: 37 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 37 KiB After Width: | Height: | Size: 39 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 23 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 23 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 9.9 KiB After Width: | Height: | Size: 10 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 18 KiB After Width: | Height: | Size: 18 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 21 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 29 KiB After Width: | Height: | Size: 30 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 24 KiB After Width: | Height: | Size: 24 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 23 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 23 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 22 KiB After Width: | Height: | Size: 22 KiB |
Binary file not shown.
|
After Width: | Height: | Size: 4.5 KiB |
File diff suppressed because it is too large
Load Diff
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1086,11 +1091,11 @@ example of the functionality of <strong>Scikit-Learn</strong>.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>The intercept alpha:
|
||||
[1.97977855]
|
||||
[2.07927777]
|
||||
Coefficient beta :
|
||||
[[5.06813806]]
|
||||
Mean squared error: 0.20
|
||||
Variance score: 0.90
|
||||
[[4.95907063]]
|
||||
Mean squared error: 0.22
|
||||
Variance score: 0.91
|
||||
Mean squared log error: 0.01
|
||||
Mean absolute error: 0.37
|
||||
</pre></div>
|
||||
@@ -1192,7 +1197,7 @@ a linear <span class="math notranslate nohighlight">\(x\)</span>-dependence we s
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<img alt="_images/chapter1_33_0.png" src="_images/chapter1_33_0.png" />
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.004999999999999996
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.005000000000000004
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1403,7 +1408,7 @@ the <em>Hadamard product</em>, meaning element-wise multiplication.</p>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Old accuracy on training data: 0.1440501043841336
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20753/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76811/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -1702,45 +1707,6 @@ Lambda = 10.0
|
||||
Accuracy score on test set: 0.925
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 1e-05
|
||||
Accuracy score on test set: 0.9472222222222222
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 0.0001
|
||||
Accuracy score on test set: 0.9277777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 0.001
|
||||
Accuracy score on test set: 0.9472222222222222
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 0.01
|
||||
Accuracy score on test set: 0.9305555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 0.1
|
||||
Accuracy score on test set: 0.9555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 1.0
|
||||
Accuracy score on test set: 0.7694444444444445
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.01
|
||||
Lambda = 10.0
|
||||
Accuracy score on test set: 0.19166666666666668
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20753/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output traceback highlight-ipythontb notranslate"><div class="highlight"><pre><span></span><span class="gt">---------------------------------------------------------------------------</span>
|
||||
<span class="ne">KeyboardInterrupt</span><span class="g g-Whitespace"> </span>Traceback (most recent call last)
|
||||
<span class="n">Cell</span> <span class="n">In</span><span class="p">[</span><span class="mi">8</span><span class="p">],</span> <span class="n">line</span> <span class="mi">11</span>
|
||||
@@ -1751,17 +1717,18 @@ Accuracy score on test set: 0.19166666666666668
|
||||
<span class="g g-Whitespace"> </span><span class="mi">13</span> <span class="n">DNN_numpy</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="n">dnn</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">15</span> <span class="n">test_predict</span> <span class="o">=</span> <span class="n">dnn</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
|
||||
|
||||
<span class="nn">Cell In[6], line 99,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="nn">Cell In[6], line 98,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">95</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">96</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="ne">---> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
<span class="ne">---> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
|
||||
<span class="nn">Cell In[6], line 64,</span> in <span class="ni">NeuralNetwork.backpropagation</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">61</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_weights_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">a_h</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">error_output</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">62</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_bias_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">error_output</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="ne">---> </span><span class="mi">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_weights_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">X_data</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">error_hidden</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">65</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_bias_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">error_hidden</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">67</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">lmbd</span> <span class="o">></span> <span class="mf">0.0</span><span class="p">:</span>
|
||||
<span class="nn">Cell In[6], line 38,</span> in <span class="ni">NeuralNetwork.feed_forward</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">36</span> <span class="k">def</span> <span class="nf">feed_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">37</span> <span class="c1"># feed-forward for training</span>
|
||||
<span class="ne">---> </span><span class="mi">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_h</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">X_data</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_bias</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">39</span> <span class="bp">self</span><span class="o">.</span><span class="n">a_h</span> <span class="o">=</span> <span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">z_h</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_o</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">a_h</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_bias</span>
|
||||
|
||||
<span class="ne">KeyboardInterrupt</span>:
|
||||
</pre></div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1335,10 +1340,10 @@ covariance matrix through the <strong>np.linalg.eig()</strong> function.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.03726977611299938
|
||||
4.262466605211622
|
||||
[[0.83354173 2.32104741]
|
||||
[2.32104741 7.32657772]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.07753675114613659
|
||||
3.7056640671387777
|
||||
[[ 1.04061312 3.10280114]
|
||||
[ 3.10280114 10.15295172]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1375,10 +1380,10 @@ a more brute force way. Here we scale the mean values for each column of the des
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.07860645184491624
|
||||
1.2936571226638978
|
||||
[[1. 0.66747609]
|
||||
[0.66747609 1. ]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.08394467351014487
|
||||
1.6207140122788155
|
||||
[[1. 0.62913273]
|
||||
[0.62913273 1. ]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1408,30 +1413,30 @@ this matrix we easily see that it is a positive definite matrix.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[-0.26697306 0.29778864]
|
||||
[-2.19869916 -6.93548204]
|
||||
[ 0.7618873 2.50605353]
|
||||
[-0.42441412 -1.40921665]
|
||||
[ 0.4871032 0.64995019]
|
||||
[ 1.20793948 2.61639509]
|
||||
[ 0.97826564 2.87523613]
|
||||
[-1.00907717 -2.99547963]
|
||||
[ 0.78152283 3.2948209 ]
|
||||
[-0.31755493 -0.90006616]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[-1.51530018 -5.52405562]
|
||||
[-0.12754161 -0.1185269 ]
|
||||
[ 1.52226126 3.76791825]
|
||||
[ 0.53838544 1.31599532]
|
||||
[ 0.62034064 2.82815583]
|
||||
[-0.57902694 -2.39362955]
|
||||
[-0.9992839 -3.26786103]
|
||||
[-1.07415889 -3.24735297]
|
||||
[ 0.61880799 2.07584629]
|
||||
[ 0.99551619 4.56351038]]
|
||||
0 1
|
||||
0 -0.266973 0.297789
|
||||
1 -2.198699 -6.935482
|
||||
2 0.761887 2.506054
|
||||
3 -0.424414 -1.409217
|
||||
4 0.487103 0.649950
|
||||
5 1.207939 2.616395
|
||||
6 0.978266 2.875236
|
||||
7 -1.009077 -2.995480
|
||||
8 0.781523 3.294821
|
||||
9 -0.317555 -0.900066
|
||||
0 -1.515300 -5.524056
|
||||
1 -0.127542 -0.118527
|
||||
2 1.522261 3.767918
|
||||
3 0.538385 1.315995
|
||||
4 0.620341 2.828156
|
||||
5 -0.579027 -2.393630
|
||||
6 -0.999284 -3.267861
|
||||
7 -1.074159 -3.247353
|
||||
8 0.618808 2.075846
|
||||
9 0.995516 4.563510
|
||||
0 1
|
||||
0 1.000000 0.978369
|
||||
1 0.978369 1.000000
|
||||
0 1.000000 0.977638
|
||||
1 0.977638 1.000000
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1488,37 +1493,37 @@ this matrix we easily see that it is a positive definite matrix.</p>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0 1 2 3 4 5 6 7 \
|
||||
0 0.0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
|
||||
1 0.0 0.090448 0.082216 0.088200 0.084006 0.079901 0.077733 0.074768
|
||||
2 0.0 0.082216 0.075560 0.081246 0.077794 0.074400 0.072599 0.070081
|
||||
3 0.0 0.088200 0.081246 0.091136 0.087474 0.083840 0.083597 0.080857
|
||||
4 0.0 0.084006 0.077794 0.087474 0.084194 0.080928 0.080799 0.078308
|
||||
5 0.0 0.079901 0.074400 0.083840 0.080928 0.078015 0.077985 0.075733
|
||||
6 0.0 0.077733 0.072599 0.083597 0.080799 0.077985 0.079026 0.076796
|
||||
7 0.0 0.074768 0.070081 0.080857 0.078308 0.075733 0.076796 0.074738
|
||||
8 0.0 0.071947 0.067679 0.078227 0.075911 0.073561 0.074636 0.072742
|
||||
9 0.0 0.069255 0.065380 0.075695 0.073598 0.071461 0.072539 0.070801
|
||||
10 0.0 0.068030 0.064276 0.075365 0.073257 0.071105 0.072914 0.071121
|
||||
11 0.0 0.065704 0.062251 0.073098 0.071167 0.069187 0.070966 0.069305
|
||||
12 0.0 0.063502 0.060329 0.070937 0.069172 0.067353 0.069098 0.067561
|
||||
13 0.0 0.061415 0.058504 0.068877 0.067267 0.065599 0.067306 0.065886
|
||||
14 0.0 0.059435 0.056769 0.066909 0.065446 0.063921 0.065586 0.064277
|
||||
1 0.0 0.064918 0.066625 0.070709 0.066738 0.062466 0.066234 0.061496
|
||||
2 0.0 0.066625 0.069854 0.074673 0.071414 0.067564 0.071285 0.066813
|
||||
3 0.0 0.070709 0.074673 0.081315 0.078121 0.074215 0.079025 0.074295
|
||||
4 0.0 0.066738 0.071414 0.078121 0.075719 0.072469 0.076899 0.072783
|
||||
5 0.0 0.062466 0.067564 0.074215 0.072469 0.069799 0.073864 0.070314
|
||||
6 0.0 0.066234 0.071285 0.079025 0.076899 0.073864 0.078892 0.074884
|
||||
7 0.0 0.061496 0.066813 0.074295 0.072783 0.070314 0.074884 0.071456
|
||||
8 0.0 0.057063 0.062501 0.069694 0.068679 0.066688 0.070846 0.067922
|
||||
9 0.0 0.052982 0.058442 0.065333 0.064718 0.063128 0.066918 0.064427
|
||||
10 0.0 0.060254 0.065730 0.073835 0.072549 0.070283 0.075233 0.071953
|
||||
11 0.0 0.055830 0.061349 0.069058 0.068223 0.066402 0.070895 0.068100
|
||||
12 0.0 0.051815 0.057304 0.064628 0.064155 0.062706 0.066794 0.064414
|
||||
13 0.0 0.048182 0.053593 0.060546 0.060365 0.059226 0.062955 0.060930
|
||||
14 0.0 0.044899 0.050198 0.056798 0.056851 0.055971 0.059383 0.057659
|
||||
|
||||
8 9 10 11 12 13 14
|
||||
0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
|
||||
1 0.071947 0.069255 0.068030 0.065704 0.063502 0.061415 0.059435
|
||||
2 0.067679 0.065380 0.064276 0.062251 0.060329 0.058504 0.056769
|
||||
3 0.078227 0.075695 0.075365 0.073098 0.070937 0.068877 0.066909
|
||||
4 0.075911 0.073598 0.073257 0.071167 0.069172 0.067267 0.065446
|
||||
5 0.073561 0.071461 0.071105 0.069187 0.067353 0.065599 0.063921
|
||||
6 0.074636 0.072539 0.072914 0.070966 0.069098 0.067306 0.065586
|
||||
7 0.072742 0.070801 0.071121 0.069305 0.067561 0.065886 0.064277
|
||||
8 0.070901 0.069107 0.069371 0.067680 0.066054 0.064491 0.062988
|
||||
9 0.069107 0.067454 0.067659 0.066088 0.064575 0.063119 0.061718
|
||||
10 0.069371 0.067659 0.068506 0.066860 0.065272 0.063740 0.062261
|
||||
11 0.067680 0.066088 0.066860 0.065318 0.063830 0.062393 0.061005
|
||||
12 0.066054 0.064575 0.065272 0.063830 0.062436 0.061089 0.059788
|
||||
13 0.064491 0.063119 0.063740 0.062393 0.061089 0.059829 0.058609
|
||||
14 0.062988 0.061718 0.062261 0.061005 0.059788 0.058609 0.057468
|
||||
1 0.057063 0.052982 0.060254 0.055830 0.051815 0.048182 0.044899
|
||||
2 0.062501 0.058442 0.065730 0.061349 0.057304 0.053593 0.050198
|
||||
3 0.069694 0.065333 0.073835 0.069058 0.064628 0.060546 0.056798
|
||||
4 0.068679 0.064718 0.072549 0.068223 0.064155 0.060365 0.056851
|
||||
5 0.066688 0.063128 0.070283 0.066402 0.062706 0.059226 0.055971
|
||||
6 0.070846 0.066918 0.075233 0.070895 0.066794 0.062955 0.059383
|
||||
7 0.067922 0.064427 0.071953 0.068100 0.064414 0.060930 0.057659
|
||||
8 0.064834 0.061731 0.068536 0.065121 0.061814 0.058658 0.055672
|
||||
9 0.061731 0.058976 0.065134 0.062107 0.059142 0.056285 0.053560
|
||||
10 0.068536 0.065134 0.072904 0.069119 0.065481 0.062027 0.058774
|
||||
11 0.065121 0.062107 0.069119 0.065772 0.062517 0.059399 0.056439
|
||||
12 0.061814 0.059142 0.065481 0.062517 0.059603 0.056786 0.054091
|
||||
13 0.058658 0.056285 0.062027 0.059399 0.056786 0.054238 0.051782
|
||||
14 0.055672 0.053560 0.058774 0.056439 0.054091 0.051782 0.049540
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -889,10 +894,10 @@ number <span class="math notranslate nohighlight">\(i\)</span> is left out. Usin
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Runtime: 0.156654 sec
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Runtime: 0.159617 sec
|
||||
Jackknife Statistics :
|
||||
original bias std. error
|
||||
100.193 100.183 0.150667
|
||||
99.9045 99.8945 0.150698
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1111,7 +1116,7 @@ theorem.</p>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Bootstrap Statistics :
|
||||
original bias std. error
|
||||
100.159 15.0085 100.157 0.150625
|
||||
99.9457 15.0851 99.9458 0.149903
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1318,7 +1323,9 @@ Error: 0.08426840630693411
|
||||
Bias^2: 0.0796891867672603
|
||||
Var: 0.004579219539673834
|
||||
0.08426840630693411 >= 0.0796891867672603 + 0.004579219539673834 = 0.08426840630693413
|
||||
Polynomial degree: 2
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 2
|
||||
Error: 0.10398646080125035
|
||||
Bias^2: 0.1007711427354898
|
||||
Var: 0.0032153180657605116
|
||||
@@ -1340,7 +1347,10 @@ Var: 0.004091940707753939
|
||||
0.05227921801205686 >= 0.0481872773043029 + 0.004091940707753939 = 0.052279218012056844
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 6
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree:
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 6
|
||||
Error: 0.037813671417389005
|
||||
Bias^2: 0.033657685071527665
|
||||
Var: 0.00415598634586135
|
||||
@@ -1360,14 +1370,14 @@ Error: 0.02660572763718093
|
||||
Bias^2: 0.010018312644137363
|
||||
Var: 0.016587414993043573
|
||||
0.02660572763718093 >= 0.010018312644137363 + 0.016587414993043573 = 0.026605727637180936
|
||||
Polynomial degree: 10
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 10
|
||||
Error: 0.021592704588025025
|
||||
Bias^2: 0.010516485576645508
|
||||
Var: 0.011076219011379514
|
||||
0.021592704588025025 >= 0.010516485576645508 + 0.011076219011379514 = 0.021592704588025022
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 11
|
||||
Polynomial degree: 11
|
||||
Error: 0.07160048164233104
|
||||
Bias^2: 0.014436800088904942
|
||||
Var: 0.05716368155342608
|
||||
@@ -1386,7 +1396,7 @@ Var: 0.20867052175034223
|
||||
0.22842468702219465 >= 0.01975416527185249 + 0.20867052175034223 = 0.2284246870221947
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/chapter3_66_4.png" src="_images/chapter3_66_4.png" />
|
||||
<img alt="_images/chapter3_66_6.png" src="_images/chapter3_66_6.png" />
|
||||
</div>
|
||||
</div>
|
||||
<p>The bias-variance tradeoff summarizes the fundamental tension in
|
||||
@@ -1607,62 +1617,64 @@ Mean squared error on test data: 123711.53703498
|
||||
Degree of polynomial: 3
|
||||
Mean squared error on training data: 9011.85263220
|
||||
Mean squared error on test data: 10913.84780262
|
||||
Degree of polynomial: 4
|
||||
Mean squared error on training data: 303.47610036
|
||||
Mean squared error on test data: 426.30787294
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 5
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 4
|
||||
Mean squared error on training data: 303.47610036
|
||||
Mean squared error on test data: 426.30787294
|
||||
Degree of polynomial: 5
|
||||
Mean squared error on training data: 3.80354994
|
||||
Mean squared error on test data: 5.98822371
|
||||
Degree of polynomial: 6
|
||||
Mean squared error on training data: 3.66204648
|
||||
Mean squared error on test data: 8.14812206
|
||||
Degree of polynomial: 7
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 7
|
||||
Mean squared error on training data: 0.47075725
|
||||
Mean squared error on test data: 2.00607783
|
||||
Degree of polynomial: 8
|
||||
Mean squared error on training data: 0.04912436
|
||||
Mean squared error on test data: 0.21596432
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 9
|
||||
Degree of polynomial: 9
|
||||
Mean squared error on training data: 0.02522069
|
||||
Mean squared error on test data: 0.08576932
|
||||
Degree of polynomial: 10
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 10
|
||||
Mean squared error on training data: 0.02511518
|
||||
Mean squared error on test data: 1.20015436
|
||||
Degree of polynomial: 11
|
||||
Mean squared error on training data: 0.01640891
|
||||
Mean squared error on test data: 1.35533773
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 12
|
||||
Degree of polynomial: 12
|
||||
Mean squared error on training data: 0.00813803
|
||||
Mean squared error on test data: 0.17446471
|
||||
Degree of polynomial: 13
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 13
|
||||
Mean squared error on training data: 0.00759119
|
||||
Mean squared error on test data: 1.08131003
|
||||
Degree of polynomial: 14
|
||||
Mean squared error on training data: 0.00472199
|
||||
Mean squared error on test data: 0.81333808
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 15
|
||||
Degree of polynomial: 15
|
||||
Mean squared error on training data: 0.00410478
|
||||
Mean squared error on test data: 92.09163947
|
||||
Degree of polynomial: 16
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 16
|
||||
Mean squared error on training data: 0.00315593
|
||||
Mean squared error on test data: 234.38827994
|
||||
Degree of polynomial: 17
|
||||
Mean squared error on training data: 0.00242999
|
||||
Mean squared error on test data: 1271.34367970
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 18
|
||||
Degree of polynomial: 18
|
||||
Mean squared error on training data: 0.00228740
|
||||
Mean squared error on test data: 108.21093775
|
||||
Degree of polynomial: 19
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 19
|
||||
Mean squared error on training data: 0.00156374
|
||||
Mean squared error on test data: 1385.79778008
|
||||
Degree of polynomial: 20
|
||||
@@ -1682,18 +1694,20 @@ Mean squared error on test data: 5567.04664255
|
||||
Degree of polynomial: 24
|
||||
Mean squared error on training data: 0.00084707
|
||||
Mean squared error on test data: 1325.26124692
|
||||
Degree of polynomial: 25
|
||||
Mean squared error on training data: 0.00079125
|
||||
Mean squared error on test data: 129012.83870189
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 26
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 25
|
||||
Mean squared error on training data: 0.00079125
|
||||
Mean squared error on test data: 129012.83870189
|
||||
Degree of polynomial: 26
|
||||
Mean squared error on training data: 0.00076908
|
||||
Mean squared error on test data: 18388.59354079
|
||||
Degree of polynomial: 27
|
||||
Mean squared error on training data: 0.00069123
|
||||
Mean squared error on test data: 2351.97979891
|
||||
Degree of polynomial: 28
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 28
|
||||
Mean squared error on training data: 0.00062592
|
||||
Mean squared error on test data: 3983.63037846
|
||||
Degree of polynomial: 29
|
||||
@@ -1701,13 +1715,13 @@ Mean squared error on training data: 0.00060704
|
||||
Mean squared error on test data: 3262.26814548
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/626635268.py:73: RuntimeWarning: divide by zero encountered in log10
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/626635268.py:73: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(trainingerror), label='Training Error')
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/626635268.py:74: RuntimeWarning: divide by zero encountered in log10
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/626635268.py:74: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(testerror), label='Test Error')
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/chapter3_69_9.png" src="_images/chapter3_69_9.png" />
|
||||
<img alt="_images/chapter3_69_11.png" src="_images/chapter3_69_11.png" />
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1937,7 +1951,7 @@ cross-validation (LOOCV).</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/3817475779.py:63: RuntimeWarning: divide by zero encountered in log10
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/3817475779.py:63: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(estimated_mse_sklearn), label='Test Error')
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2826,7 +2840,7 @@ linear system as an equation would reduce this down to
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/4162706317.py:7: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/4162706317.py:7: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
cb.ax.set_yticklabels(cb.ax.get_yticklabels(), fontsize=18)
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2970,7 +2984,7 @@ with the form utilized in linear regression, viz.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/3777801602.py:7: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/3777801602.py:7: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
cb.ax.set_yticklabels(cb.ax.get_yticklabels(), fontsize=18)
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3010,7 +3024,7 @@ cost function is given by</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/438060758.py:10: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/438060758.py:10: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
cb.ax.set_yticklabels(cb.ax.get_yticklabels(), fontsize=18)
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3045,7 +3059,7 @@ cost function is given by</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20789/3544313922.py:9: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76898/3544313922.py:9: UserWarning: set_ticklabels() should only be used with a fixed number of ticks, i.e. after set_ticks() or using a FixedLocator.
|
||||
cb.ax.set_yticklabels(cb.ax.get_yticklabels(), fontsize=18)
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3098,43 +3112,43 @@ constant as opposed to ridge and OLS. We get a sparse solution with
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0%| | 0/10 [00:00<?, ?it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0%| | 0/10 [00:00<?, ?it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/Users/mhjensen/miniforge3/envs/myenv/lib/python3.9/site-packages/sklearn/linear_model/_coordinate_descent.py:628: ConvergenceWarning: Objective did not converge. You might want to increase the number of iterations, check the scale of the features or consider increasing regularisation. Duality gap: 3.924e+00, tolerance: 1.797e+00
|
||||
model = cd_fast.enet_coordinate_descent(
|
||||
|
||||
10%|██████████ | 1/10 [00:00<00:06, 1.30it/s]
|
||||
10%|█████████████▍ | 1/10 [00:01<00:10, 1.18s/it]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 20%|████████████████████ | 2/10 [00:01<00:06, 1.25it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 20%|██████████████████████████▊ | 2/10 [00:02<00:09, 1.13s/it]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 30%|██████████████████████████████ | 3/10 [00:02<00:04, 1.44it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 30%|████████████████████████████████████████▏ | 3/10 [00:03<00:07, 1.00s/it]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 40%|████████████████████████████████████████ | 4/10 [00:02<00:03, 1.52it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 40%|█████████████████████████████████████████████████████▌ | 4/10 [00:03<00:05, 1.07it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 50%|██████████████████████████████████████████████████ | 5/10 [00:03<00:03, 1.53it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 50%|███████████████████████████████████████████████████████████████████ | 5/10 [00:04<00:04, 1.15it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 60%|████████████████████████████████████████████████████████████ | 6/10 [00:04<00:02, 1.54it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 60%|████████████████████████████████████████████████████████████████████████████████▍ | 6/10 [00:05<00:03, 1.19it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 70%|██████████████████████████████████████████████████████████████████████ | 7/10 [00:04<00:02, 1.46it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 70%|█████████████████████████████████████████████████████████████████████████████████████████████▊ | 7/10 [00:06<00:02, 1.25it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 80%|████████████████████████████████████████████████████████████████████████████████ | 8/10 [00:05<00:01, 1.49it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 80%|███████████████████████████████████████████████████████████████████████████████████████████████████████████▏ | 8/10 [00:07<00:01, 1.24it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 90%|██████████████████████████████████████████████████████████████████████████████████████████ | 9/10 [00:06<00:00, 1.50it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 90%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████▌ | 9/10 [00:07<00:00, 1.18it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:06<00:00, 1.55it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:08<00:00, 1.19it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|███████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:06<00:00, 1.49it/s]
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:08<00:00, 1.14it/s]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -817,9 +822,9 @@ predicting the target features of query instances is as follows:</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2nd degree coefficients:
|
||||
zero power: -0.7397605907501061
|
||||
first power: 0.007373805280423706
|
||||
second power: 0.00026005429911763394
|
||||
zero power: -4.655365720948307
|
||||
first power: 0.09332315952999948
|
||||
second power: -0.0004298347114567659
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/chapter6_1_1.png" src="_images/chapter6_1_1.png" />
|
||||
@@ -1682,12 +1687,8 @@ attributes at each step while growing the tree.</p>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>(426, 30)
|
||||
(143, 30)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test set accuracy with Logistic Regression: 0.94
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test set accuracy with SVM: 0.63
|
||||
Test set accuracy with Logistic Regression: 0.94
|
||||
Test set accuracy with SVM: 0.63
|
||||
Test set accuracy with Decision Trees: 0.90
|
||||
Test set accuracy Logistic Regression with scaled data: 0.96
|
||||
Test set accuracy SVM with scaled data: 0.96
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -771,10 +776,10 @@ covariance matrix through the <strong>np.linalg.eig()</strong> function.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.0610096522011426
|
||||
3.8847504075456363
|
||||
[[ 1.07280604 3.11827698]
|
||||
[ 3.11827698 10.20730033]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.07475005787902417
|
||||
4.35510226157812
|
||||
[[ 1.02595928 3.2527634 ]
|
||||
[ 3.2527634 11.12684733]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -814,10 +819,10 @@ a more brute force way. Here we scale the mean values for each column of the des
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.08699604706693358
|
||||
1.8785678201327416
|
||||
[[1. 0.67701729]
|
||||
[0.67701729 1. ]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.0746776881193676
|
||||
1.7289381470678358
|
||||
[[1. 0.74948572]
|
||||
[0.74948572 1. ]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -846,32 +851,30 @@ this matrix we easily see that it is a positive definite matrix.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[-0.56439048 -1.59243304]
|
||||
[ 0.34744134 -0.79671424]
|
||||
[-1.55842946 -5.7693748 ]
|
||||
[ 0.1084649 0.43675706]
|
||||
[-0.34689964 -0.80973749]
|
||||
[ 0.54581307 1.66293202]
|
||||
[-0.38075194 -0.87904563]
|
||||
[ 0.89964122 5.25714271]
|
||||
[ 0.67258465 1.91633883]
|
||||
[ 0.27652633 0.57413459]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0 1
|
||||
0 -0.564390 -1.592433
|
||||
1 0.347441 -0.796714
|
||||
2 -1.558429 -5.769375
|
||||
3 0.108465 0.436757
|
||||
4 -0.346900 -0.809737
|
||||
5 0.545813 1.662932
|
||||
6 -0.380752 -0.879046
|
||||
7 0.899641 5.257143
|
||||
8 0.672585 1.916339
|
||||
9 0.276526 0.574135
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[-0.16405003 0.54955605]
|
||||
[-0.11637304 -0.7621305 ]
|
||||
[ 0.01996582 1.48906628]
|
||||
[-0.79270207 -3.3173567 ]
|
||||
[ 0.52745417 2.2316734 ]
|
||||
[ 1.34172766 4.48299299]
|
||||
[-0.60711982 -1.1103761 ]
|
||||
[-1.56812901 -5.66825374]
|
||||
[ 0.74859587 2.31737432]
|
||||
[ 0.61063045 -0.212546 ]]
|
||||
0 1
|
||||
0 1.000000 0.932605
|
||||
1 0.932605 1.000000
|
||||
0 -0.164050 0.549556
|
||||
1 -0.116373 -0.762131
|
||||
2 0.019966 1.489066
|
||||
3 -0.792702 -3.317357
|
||||
4 0.527454 2.231673
|
||||
5 1.341728 4.482993
|
||||
6 -0.607120 -1.110376
|
||||
7 -1.568129 -5.668254
|
||||
8 0.748596 2.317374
|
||||
9 0.610630 -0.212546
|
||||
0 1
|
||||
0 1.000000 0.933053
|
||||
1 0.933053 1.000000
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -928,37 +931,37 @@ this matrix we easily see that it is a positive definite matrix.</p>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0 1 2 3 4 5 6 7 \
|
||||
0 0.0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
|
||||
1 0.0 0.079059 0.081365 0.076315 0.081270 0.086391 0.066334 0.070891
|
||||
2 0.0 0.081365 0.085489 0.076059 0.081793 0.087930 0.064777 0.069667
|
||||
3 0.0 0.076315 0.076059 0.078398 0.082223 0.085871 0.071052 0.075199
|
||||
4 0.0 0.081270 0.081793 0.082223 0.086686 0.091074 0.073735 0.078326
|
||||
5 0.0 0.086391 0.087930 0.085871 0.091074 0.096339 0.076078 0.081151
|
||||
6 0.0 0.066334 0.064777 0.071052 0.073735 0.076078 0.066329 0.069696
|
||||
7 0.0 0.070891 0.069667 0.075199 0.078326 0.081151 0.069696 0.073438
|
||||
8 0.0 0.075831 0.075047 0.079570 0.083213 0.086609 0.073167 0.077326
|
||||
9 0.0 0.081169 0.080964 0.084139 0.088383 0.092454 0.076692 0.081316
|
||||
10 0.0 0.057338 0.055249 0.063213 0.065107 0.066605 0.060295 0.063007
|
||||
11 0.0 0.061147 0.059192 0.066951 0.069155 0.070974 0.063515 0.066524
|
||||
12 0.0 0.065303 0.063532 0.070967 0.073529 0.075723 0.066934 0.070275
|
||||
13 0.0 0.069840 0.068317 0.075276 0.078251 0.080886 0.070553 0.074265
|
||||
14 0.0 0.074791 0.073599 0.079886 0.083341 0.086493 0.074366 0.078493
|
||||
1 0.0 0.091870 0.082074 0.092077 0.086967 0.081650 0.082936 0.079181
|
||||
2 0.0 0.082074 0.074742 0.080377 0.076475 0.072462 0.071634 0.068667
|
||||
3 0.0 0.092077 0.080377 0.097651 0.091384 0.084848 0.091276 0.086696
|
||||
4 0.0 0.086967 0.076475 0.091384 0.085807 0.079987 0.084996 0.080907
|
||||
5 0.0 0.081650 0.072462 0.084848 0.079987 0.074920 0.078475 0.074883
|
||||
6 0.0 0.082936 0.071634 0.091276 0.084996 0.078475 0.087603 0.082951
|
||||
7 0.0 0.079181 0.068667 0.086696 0.080907 0.074883 0.082951 0.078670
|
||||
8 0.0 0.075515 0.065793 0.082200 0.076895 0.071365 0.078384 0.074464
|
||||
9 0.0 0.071891 0.062978 0.077729 0.072907 0.067875 0.073847 0.070281
|
||||
10 0.0 0.073837 0.063468 0.083409 0.077459 0.071310 0.081647 0.077164
|
||||
11 0.0 0.070649 0.060893 0.079551 0.073998 0.068246 0.077709 0.073536
|
||||
12 0.0 0.067610 0.058445 0.075858 0.070684 0.065314 0.073933 0.070055
|
||||
13 0.0 0.064698 0.056110 0.072302 0.067495 0.062496 0.070295 0.066700
|
||||
14 0.0 0.061891 0.053872 0.068856 0.064406 0.059771 0.066768 0.063444
|
||||
|
||||
8 9 10 11 12 13 14
|
||||
0 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000
|
||||
1 0.075831 0.081169 0.057338 0.061147 0.065303 0.069840 0.074791
|
||||
2 0.075047 0.080964 0.055249 0.059192 0.063532 0.068317 0.073599
|
||||
3 0.079570 0.084139 0.063213 0.066951 0.070967 0.075276 0.079886
|
||||
4 0.083213 0.088383 0.065107 0.069155 0.073529 0.078251 0.083341
|
||||
5 0.086609 0.092454 0.066605 0.070974 0.075723 0.080886 0.086493
|
||||
6 0.073167 0.076692 0.060295 0.063515 0.066934 0.070553 0.074366
|
||||
7 0.077326 0.081316 0.063007 0.066524 0.070275 0.074265 0.078493
|
||||
8 0.081683 0.086203 0.065751 0.069590 0.073705 0.078104 0.082794
|
||||
9 0.086203 0.091326 0.068471 0.072660 0.077172 0.082023 0.087227
|
||||
10 0.065751 0.068471 0.055720 0.058436 0.061294 0.064287 0.067400
|
||||
11 0.069590 0.072660 0.058436 0.061405 0.064542 0.067841 0.071290
|
||||
12 0.073705 0.077172 0.061294 0.064542 0.067986 0.071624 0.075448
|
||||
13 0.078104 0.082023 0.064287 0.067841 0.071624 0.075640 0.079883
|
||||
14 0.082794 0.087227 0.067400 0.071290 0.075448 0.079883 0.084595
|
||||
1 0.075515 0.071891 0.073837 0.070649 0.067610 0.064698 0.061891
|
||||
2 0.065793 0.062978 0.063468 0.060893 0.058445 0.056110 0.053872
|
||||
3 0.082200 0.077729 0.083409 0.079551 0.075858 0.072302 0.068856
|
||||
4 0.076895 0.072907 0.077459 0.073998 0.070684 0.067495 0.064406
|
||||
5 0.071365 0.067875 0.071310 0.068246 0.065314 0.062496 0.059771
|
||||
6 0.078384 0.073847 0.081647 0.077709 0.073933 0.070295 0.066768
|
||||
7 0.074464 0.070281 0.077164 0.073536 0.070055 0.066700 0.063444
|
||||
8 0.070610 0.066774 0.072769 0.069439 0.066244 0.063164 0.060174
|
||||
9 0.066774 0.063285 0.068412 0.065374 0.062458 0.059646 0.056918
|
||||
10 0.072769 0.068412 0.077270 0.073441 0.069770 0.066233 0.062805
|
||||
11 0.069439 0.065374 0.073441 0.069876 0.066455 0.063158 0.059960
|
||||
12 0.066244 0.062458 0.069770 0.066455 0.063273 0.060204 0.057225
|
||||
13 0.063164 0.059646 0.066233 0.063158 0.060204 0.057353 0.054585
|
||||
14 0.060174 0.056918 0.062805 0.059960 0.057225 0.054585 0.052021
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1147,10 +1150,10 @@ We can write our own code or simply use either the functionaly of <strong>numpy<
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span> 0 1
|
||||
0 4.021032 1.990843
|
||||
1 1.990843 1.969959
|
||||
[[4.02103235 1.99084335]
|
||||
[1.99084335 1.9699594 ]]
|
||||
0 4.070272 2.059136
|
||||
1 2.059136 2.054311
|
||||
[[4.07027208 2.05913631]
|
||||
[2.05913631 2.05431096]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1177,8 +1180,8 @@ Our own code here is not very elegant and asks for obvious improvements. It is t
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Centered covariance using own code
|
||||
[[4.02103235 1.99084335]
|
||||
[1.99084335 1.9699594 ]]
|
||||
[[4.07027208 2.05913631]
|
||||
[2.05913631 2.05431096]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/chapter8_65_1.png" src="_images/chapter8_65_1.png" />
|
||||
@@ -1238,16 +1241,16 @@ questions.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvalues of Covariance matrix
|
||||
5.234956145890017
|
||||
0.7560356057040467
|
||||
5.3549029458698545
|
||||
0.7696800897647572
|
||||
First eigenvector
|
||||
[0.85379714 0.52060584]
|
||||
[0.84842937 0.5293086 ]
|
||||
Second eigenvector
|
||||
[-0.52060584 0.85379714]
|
||||
[-0.5293086 0.84842937]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvector of largest eigenvalue
|
||||
[-0.85379714 -0.52060584]
|
||||
[-0.84842937 -0.5293086 ]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -351,6 +351,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -824,15 +829,15 @@ regression.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[3.72796854]
|
||||
[3.26269704]]
|
||||
Eigenvalues of Hessian Matrix:[0.26876494 4.16606994]
|
||||
[[3.7056279 ]
|
||||
[3.11632514]]
|
||||
Eigenvalues of Hessian Matrix:[0.27378241 4.9133261 ]
|
||||
theta from own gd
|
||||
[[3.72796854]
|
||||
[3.26269704]]
|
||||
[[3.7056279 ]
|
||||
[3.11632514]]
|
||||
theta from own sdg
|
||||
[[3.70521262]
|
||||
[3.29966563]]
|
||||
[[3.62227539]
|
||||
[3.09214577]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_5_1.png" src="_images/exercisesweek41_5_1.png" />
|
||||
@@ -954,15 +959,17 @@ first example shows results with ordinary leats squares.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[3.89549614]
|
||||
[2.9788957 ]]
|
||||
Eigenvalues of Hessian Matrix:[0.34210288 4.43495138]
|
||||
theta from own gd
|
||||
[[3.89549614]
|
||||
[2.9788957 ]]
|
||||
[[4.39586211]
|
||||
[2.54142449]]
|
||||
Eigenvalues of Hessian Matrix:[0.29253829 4.61759155]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_16_1.png" src="_images/exercisesweek41_16_1.png" />
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own gd
|
||||
[[4.39586211]
|
||||
[2.54142449]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_16_2.png" src="_images/exercisesweek41_16_2.png" />
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1030,73 +1037,73 @@ theta from own gd
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.]
|
||||
[3.]]
|
||||
Eigenvalues of Hessian Matrix:[0.35622964 3.83344349]
|
||||
0 [-10.84597523] [-10.53597191]
|
||||
1 [-0.41603353] [0.39392645]
|
||||
2 [-0.37737287] [0.35732012]
|
||||
3 [-0.34230481] [0.32411551]
|
||||
4 [-0.31049552] [0.29399649]
|
||||
5 [-0.28164216] [0.26667634]
|
||||
6 [-0.25547006] [0.24189496]
|
||||
7 [-0.23173004] [0.21941643]
|
||||
8 [-0.21019611] [0.19902677]
|
||||
9 [-0.19066326] [0.18053184]
|
||||
10 [-0.17294553] [0.1637556]
|
||||
11 [-0.15687426] [0.14853831]
|
||||
12 [-0.14229643] [0.13473512]
|
||||
13 [-0.12907328] [0.12221462]
|
||||
14 [-0.11707891] [0.11085761]
|
||||
15 [-0.10619914] [0.10055596]
|
||||
16 [-0.0963304] [0.09121162]
|
||||
17 [-0.08737872] [0.08273561]
|
||||
18 [-0.0792589] [0.07504726]
|
||||
19 [-0.07189362] [0.06807336]
|
||||
20 [-0.06521278] [0.06174752]
|
||||
21 [-0.05915276] [0.05600952]
|
||||
22 [-0.05365588] [0.05080473]
|
||||
23 [-0.04866982] [0.04608361]
|
||||
24 [-0.04414708] [0.04180121]
|
||||
25 [-0.04004464] [0.03791676]
|
||||
26 [-0.03632342] [0.03439327]
|
||||
27 [-0.032948] [0.03119722]
|
||||
28 [-0.02988625] [0.02829816]
|
||||
29 [-0.02710901] [0.0256685]
|
||||
Eigenvalues of Hessian Matrix:[0.28360073 4.6466172 ]
|
||||
0 [-12.76941488] [-15.71728253]
|
||||
1 [-0.06385864] [0.05142606]
|
||||
2 [-0.0599611] [0.04828733]
|
||||
3 [-0.05630145] [0.04534017]
|
||||
4 [-0.05286516] [0.04257289]
|
||||
5 [-0.0496386] [0.0399745]
|
||||
6 [-0.04660896] [0.03753471]
|
||||
7 [-0.04376424] [0.03524382]
|
||||
8 [-0.04109314] [0.03309276]
|
||||
9 [-0.03858507] [0.03107298]
|
||||
10 [-0.03623008] [0.02917648]
|
||||
11 [-0.03401882] [0.02739573]
|
||||
12 [-0.03194252] [0.02572366]
|
||||
13 [-0.02999295] [0.02415365]
|
||||
14 [-0.02816236] [0.02267946]
|
||||
15 [-0.02644351] [0.02129525]
|
||||
16 [-0.02482956] [0.01999552]
|
||||
17 [-0.02331412] [0.01877511]
|
||||
18 [-0.02189117] [0.0176292]
|
||||
19 [-0.02055507] [0.01655322]
|
||||
20 [-0.01930051] [0.01554291]
|
||||
21 [-0.01812253] [0.01459427]
|
||||
22 [-0.01701644] [0.01370353]
|
||||
23 [-0.01597786] [0.01286715]
|
||||
24 [-0.01500267] [0.01208182]
|
||||
25 [-0.014087] [0.01134442]
|
||||
26 [-0.01322722] [0.01065202]
|
||||
27 [-0.01241991] [0.01000189]
|
||||
28 [-0.01166188] [0.00939144]
|
||||
29 [-0.01095011] [0.00881824]
|
||||
theta from own gd
|
||||
[[3.93097189]
|
||||
[3.06536011]]
|
||||
0 [-0.02458986] [0.02328321]
|
||||
1 [-0.0223048] [0.02111958]
|
||||
2 [-0.01954657] [0.01850791]
|
||||
3 [-0.0169027] [0.01600453]
|
||||
4 [-0.01453883] [0.01376627]
|
||||
5 [-0.01247862] [0.01181553]
|
||||
6 [-0.01070096] [0.01013233]
|
||||
7 [-0.00917325] [0.00868581]
|
||||
8 [-0.0078625] [0.00744471]
|
||||
9 [-0.00673864] [0.00638056]
|
||||
10 [-0.00577528] [0.00546839]
|
||||
11 [-0.00494959] [0.00468658]
|
||||
12 [-0.00424194] [0.00401653]
|
||||
13 [-0.00363545] [0.00344227]
|
||||
14 [-0.00311567] [0.00295011]
|
||||
15 [-0.00267021] [0.00252832]
|
||||
16 [-0.00228844] [0.00216684]
|
||||
17 [-0.00196125] [0.00185703]
|
||||
18 [-0.00168084] [0.00159152]
|
||||
19 [-0.00144052] [0.00136398]
|
||||
20 [-0.00123456] [0.00116896]
|
||||
21 [-0.00105805] [0.00100183]
|
||||
22 [-0.00090678] [0.00085859]
|
||||
23 [-0.00077713] [0.00073584]
|
||||
24 [-0.00066602] [0.00063063]
|
||||
25 [-0.0005708] [0.00054047]
|
||||
26 [-0.00048919] [0.00046319]
|
||||
27 [-0.00041925] [0.00039697]
|
||||
28 [-0.0003593] [0.00034021]
|
||||
29 [-0.00030793] [0.00029157]
|
||||
[[3.96374557]
|
||||
[3.02919609]]
|
||||
0 [-0.01028178] [0.00828003]
|
||||
1 [-0.00965425] [0.00777467]
|
||||
2 [-0.00887675] [0.00714854]
|
||||
3 [-0.00810172] [0.0065244]
|
||||
4 [-0.00737473] [0.00593895]
|
||||
5 [-0.00670653] [0.00540084]
|
||||
6 [-0.00609674] [0.00490977]
|
||||
7 [-0.0055417] [0.00446279]
|
||||
8 [-0.00503695] [0.00405631]
|
||||
9 [-0.00457811] [0.0036868]
|
||||
10 [-0.00416103] [0.00335092]
|
||||
11 [-0.00378195] [0.00304564]
|
||||
12 [-0.00343739] [0.00276817]
|
||||
13 [-0.00312423] [0.00251598]
|
||||
14 [-0.0028396] [0.00228676]
|
||||
15 [-0.0025809] [0.00207843]
|
||||
16 [-0.00234577] [0.00188907]
|
||||
17 [-0.00213205] [0.00171697]
|
||||
18 [-0.00193781] [0.00156054]
|
||||
19 [-0.00176127] [0.00141837]
|
||||
20 [-0.00160081] [0.00128915]
|
||||
21 [-0.00145497] [0.0011717]
|
||||
22 [-0.00132241] [0.00106495]
|
||||
23 [-0.00120193] [0.00096793]
|
||||
24 [-0.00109243] [0.00087975]
|
||||
25 [-0.00099291] [0.0007996]
|
||||
26 [-0.00090245] [0.00072675]
|
||||
27 [-0.00082023] [0.00066054]
|
||||
28 [-0.0007455] [0.00060036]
|
||||
29 [-0.00067758] [0.00054567]
|
||||
theta from own gd wth momentum
|
||||
[[3.99925917]
|
||||
[3.00070146]]
|
||||
[[3.99782845]
|
||||
[3.00174877]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1149,17 +1156,17 @@ theta from own gd wth momentum
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[3.86751196]
|
||||
[3.13877544]]
|
||||
Eigenvalues of Hessian Matrix:[0.29322629 4.30627615]
|
||||
0 [-14.05912765] [-16.736807]
|
||||
1 [-2.16077156e-14] [-1.19631285e-14]
|
||||
2 [-1.70002901e-16] [-1.23687362e-16]
|
||||
3 [-1.70002901e-16] [-1.23687362e-16]
|
||||
4 [-1.70002901e-16] [-1.23687362e-16]
|
||||
[[3.60911869]
|
||||
[3.33987045]]
|
||||
Eigenvalues of Hessian Matrix:[0.31385073 4.08833652]
|
||||
0 [-17.89749468] [-19.42504764]
|
||||
1 [-6.56419363e-15] [-6.5758826e-15]
|
||||
2 [-4.99600361e-16] [-5.64393388e-16]
|
||||
3 [-4.99600361e-16] [-5.64393388e-16]
|
||||
4 [-4.99600361e-16] [-5.64393388e-16]
|
||||
beta from own Newton code
|
||||
[[3.86751196]
|
||||
[3.13877544]]
|
||||
[[3.60911869]
|
||||
[3.33987045]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1248,22 +1255,20 @@ beta from own Newton code
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[3.90340018]
|
||||
[3.20732292]]
|
||||
Eigenvalues of Hessian Matrix:[0.30252911 4.09446058]
|
||||
[[4.41451936]
|
||||
[2.55289042]]
|
||||
Eigenvalues of Hessian Matrix:[0.33812981 4.19713213]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own gd
|
||||
[[3.90340018]
|
||||
[3.20732292]]
|
||||
[[4.41451936]
|
||||
[2.55289042]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_22_2.png" src="_images/exercisesweek41_22_2.png" />
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[3.86364839]
|
||||
[3.23799188]]
|
||||
[[4.38642255]
|
||||
[2.56985133]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1345,15 +1350,17 @@ Eigenvalues of Hessian Matrix:[0.30252911 4.09446058]
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.38463079]
|
||||
[2.57169626]]
|
||||
Eigenvalues of Hessian Matrix:[0.27355018 4.06502525]
|
||||
[[3.89425071]
|
||||
[3.03737777]]
|
||||
Eigenvalues of Hessian Matrix:[0.32691458 3.94394646]
|
||||
theta from own gd
|
||||
[[4.38343773]
|
||||
[2.57278714]]
|
||||
theta from own sdg with momentum
|
||||
[[4.35254442]
|
||||
[2.58244397]]
|
||||
[[3.89408559]
|
||||
[3.03753095]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg with momentum
|
||||
[[3.92801972]
|
||||
[3.02259232]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1428,9 +1435,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own AdaGrad
|
||||
[[2.0000375 ]
|
||||
[2.99981967]
|
||||
[4.00017395]]
|
||||
[[1.99987339]
|
||||
[3.00070766]
|
||||
[3.99931264]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1512,9 +1519,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own RMSprop
|
||||
[[1.99998686]
|
||||
[2.9995237 ]
|
||||
[4.00046845]]
|
||||
[[1.99430797]
|
||||
[3.0204309 ]
|
||||
[3.97790579]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1600,9 +1607,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own ADAM
|
||||
[[1.99990776]
|
||||
[3.0005044 ]
|
||||
[3.99956442]]
|
||||
[[1.99988575]
|
||||
[3.00066222]
|
||||
[3.99946201]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1675,7 +1682,7 @@ It provides composable transformations of Python+NumPy programs: differentiate,
|
||||
return asarray(x, dtype=self.dtype)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x11edfa8b0>]
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x12288f460>]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_39_2.png" src="_images/exercisesweek41_39_2.png" />
|
||||
@@ -1710,7 +1717,7 @@ It provides composable transformations of Python+NumPy programs: differentiate,
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><matplotlib.collections.PathCollection at 0x11ef1aac0>
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><matplotlib.collections.PathCollection at 0x110657310>
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/exercisesweek41_41_1.png" src="_images/exercisesweek41_41_1.png" />
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -349,6 +349,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -350,6 +350,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -673,8 +678,8 @@ matrices and vectors.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[ 0.32001824 -0.74192227 0.29589074 0.79474214 0.93002171 -0.3039884
|
||||
-0.23453753 0.42163714 0.38469469 -0.16425426]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[-0.16520328 1.62291487 -1.6087843 0.42672668 -0.54245399 -0.47389944
|
||||
1.54395649 0.30474374 0.88958816 1.67644921]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -895,26 +900,26 @@ as (recall that we user lowercase letters for vectors and uppercase letters for
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[0.82195744 0.3891388 0.6393255 0.23848657 0.94055712 0.09024338
|
||||
0.37413588 0.74761567 0.35435219 0.07518155]
|
||||
[0.38479849 0.78036158 0.21824173 0.13664315 0.21480211 0.52460926
|
||||
0.89595918 0.25702102 0.46918325 0.00800661]
|
||||
[0.48745365 0.65375675 0.41048039 0.738242 0.68043741 0.42684131
|
||||
0.68546404 0.40826579 0.52793214 0.7031337 ]
|
||||
[0.07395645 0.49563003 0.53379115 0.81702472 0.00841458 0.72858608
|
||||
0.30840554 0.47836061 0.2180387 0.45175115]
|
||||
[0.36057178 0.55188499 0.48122761 0.1403625 0.56938055 0.04170341
|
||||
0.81077908 0.74066856 0.87234539 0.77231525]
|
||||
[0.4271294 0.25172651 0.83065295 0.37772591 0.79299228 0.80941284
|
||||
0.51579138 0.45860296 0.80070169 0.07136868]
|
||||
[0.00355788 0.63534832 0.84438755 0.30356855 0.20488577 0.24956991
|
||||
0.06192181 0.42523073 0.09314326 0.14371995]
|
||||
[0.74985547 0.10252946 0.3477494 0.32907268 0.41745457 0.38472307
|
||||
0.16382994 0.55656086 0.84104054 0.03111555]
|
||||
[0.83749554 0.84073416 0.69347409 0.82022408 0.04823618 0.34401751
|
||||
0.72546035 0.60205311 0.22177506 0.58325333]
|
||||
[0.30521597 0.84357837 0.8955058 0.17549914 0.96618572 0.86987923
|
||||
0.03103759 0.44019341 0.30819287 0.07016861]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[0.28784593 0.96321926 0.20866637 0.95849867 0.92941344 0.1506968
|
||||
0.22840543 0.0920889 0.80793317 0.50389563]
|
||||
[0.17183189 0.20143625 0.45450913 0.00646788 0.86626878 0.08925572
|
||||
0.52334702 0.03991659 0.35369204 0.78536632]
|
||||
[0.16039093 0.84796642 0.82292496 0.94439363 0.30258327 0.61219766
|
||||
0.73629812 0.16934353 0.17379702 0.04679308]
|
||||
[0.63996185 0.11274165 0.25945116 0.89423541 0.22346992 0.21007634
|
||||
0.36949491 0.48033198 0.62082039 0.32646485]
|
||||
[0.74365467 0.7733283 0.7928694 0.77278596 0.58641617 0.32914379
|
||||
0.84818156 0.91522307 0.69515573 0.58154488]
|
||||
[0.31956141 0.10975592 0.3919079 0.90613668 0.5978168 0.96954883
|
||||
0.92380565 0.41038312 0.32288529 0.55800813]
|
||||
[0.81494889 0.50633361 0.99792993 0.31899022 0.78486135 0.8728734
|
||||
0.01932215 0.67005078 0.19206115 0.83068485]
|
||||
[0.83903596 0.48440335 0.66923495 0.46990302 0.80674666 0.96465867
|
||||
0.23114262 0.71841354 0.23608218 0.10929587]
|
||||
[0.94970686 0.08965584 0.07768608 0.19814125 0.38472539 0.36807444
|
||||
0.29740527 0.95391872 0.21994185 0.13166051]
|
||||
[0.88743493 0.10721234 0.91281804 0.15125714 0.58166986 0.37588174
|
||||
0.12925014 0.00524148 0.93747994 0.33514166]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -974,13 +979,13 @@ covariance matrix through the <strong>np.linalg.eig()</strong> function.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.0005546012958340718
|
||||
4.201607904119753
|
||||
-0.10755063024965804
|
||||
[[ 1.0024984 3.08394521 3.01944109]
|
||||
[ 3.08394521 10.46598005 8.68420144]
|
||||
[ 3.01944109 8.68420144 13.58893352]]
|
||||
[21.74071459 0.05707756 3.25961982]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.08051403053372341
|
||||
3.7140333805249566
|
||||
-0.380671880038213
|
||||
[[ 0.92926923 2.65811424 2.52618757]
|
||||
[ 2.65811424 8.74246828 7.24691709]
|
||||
[ 2.52618757 7.24691709 11.65085456]]
|
||||
[18.34869216 0.09587752 2.87802239]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
Binary file not shown.
@@ -56,7 +56,7 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Project 2 on Machine Learning, deadline November 4 (Midnight)" href="project2.html" />
|
||||
<link rel="prev" title="Week 44, Convolutional Neural Networks (CNN)" href="week44.html" />
|
||||
<link rel="prev" title="Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)" href="week45.html" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
<meta name="docsearch:language" content="None">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1099,11 +1104,11 @@ of code developers and contributors keeps increasing.</p>
|
||||
|
||||
<!-- Previous / next buttons -->
|
||||
<div class='prev-next-area'>
|
||||
<a class='left-prev' id="prev-link" href="week44.html" title="previous page">
|
||||
<a class='left-prev' id="prev-link" href="week45.html" title="previous page">
|
||||
<i class="fas fa-angle-left"></i>
|
||||
<div class="prev-next-info">
|
||||
<p class="prev-next-subtitle">previous</p>
|
||||
<p class="prev-next-title">Week 44, Convolutional Neural Networks (CNN)</p>
|
||||
<p class="prev-next-title">Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)</p>
|
||||
</div>
|
||||
</a>
|
||||
<a class='right-next' id="next-link" href="project2.html" title="next page">
|
||||
|
||||
@@ -352,6 +352,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -28,7 +28,7 @@ display(data_pandas)
|
||||
|
||||
[0;31m---------------------------------------------------------------------------[0m
|
||||
[0;31mAttributeError[0m Traceback (most recent call last)
|
||||
[0;32m/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20912/1326197715.py[0m in [0;36m?[0;34m()[0m
|
||||
[0;32m/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77069/1326197715.py[0m in [0;36m?[0;34m()[0m
|
||||
[0;32m----> 6[0;31m new_hobbit = {'First Name': ["Peregrin"],
|
||||
[0m[1;32m 7[0m [0;34m'Last Name'[0m[0;34m:[0m [0;34m[[0m[0;34m"Took"[0m[0;34m][0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
|
||||
[1;32m 8[0m [0;34m'Place of birth'[0m[0;34m:[0m [0;34m[[0m[0;34m"Shire"[0m[0;34m][0m[0;34m,[0m[0;34m[0m[0;34m[0m[0m
|
||||
|
||||
@@ -351,6 +351,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -355,6 +355,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
File diff suppressed because one or more lines are too long
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1045,27 +1050,27 @@ uncorrelated.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>2.0607697355132246
|
||||
[[ 4.55115556 10.33932482 8.1013878 7.00335444 8.25896648 12.4484389
|
||||
5.43771659 2.97702119 1.56381399 8.22843017]
|
||||
[10.33932482 23.48889999 18.40474994 15.91023542 18.76273751 28.28038982
|
||||
12.35341606 6.76320304 3.55267592 18.69336507]
|
||||
[ 8.1013878 18.40474994 14.42105932 12.4664801 14.70156083 22.15912635
|
||||
9.67953091 5.29931417 2.7837026 14.64720399]
|
||||
[ 7.00335444 15.91023542 12.4664801 10.77681762 12.70896343 19.15575698
|
||||
8.36760163 4.58106393 2.40640942 12.66197393]
|
||||
[ 8.25896648 18.76273751 14.70156083 12.70896343 14.98751832 22.59013965
|
||||
9.86780577 5.40239021 2.83784791 14.9321042 ]
|
||||
[12.4484389 28.28038982 22.15912635 19.15575698 22.59013965 34.04929344
|
||||
14.87338368 8.14282569 4.27738464 22.50661596]
|
||||
[ 5.43771659 12.35341606 9.67953091 8.36760163 9.86780577 14.87338368
|
||||
6.49697893 3.55694226 1.86844355 9.83132102]
|
||||
[ 2.97702119 6.76320304 5.29931417 4.58106393 5.40239021 8.14282569
|
||||
3.55694226 1.94734174 1.02292864 5.38241567]
|
||||
[ 1.56381399 3.55267592 2.7837026 2.40640942 2.83784791 4.27738464
|
||||
1.86844355 1.02292864 0.53733918 2.82735539]
|
||||
[ 8.22843017 18.69336507 14.64720399 12.66197393 14.9321042 22.50661596
|
||||
9.83132102 5.38241567 2.82735539 14.87689496]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>3.56625717949593
|
||||
[[ 1.06428266 0.38523213 1.79328214 2.08565179 2.50663068 6.8647244
|
||||
3.38978208 3.14317326 1.71034931 3.18370342]
|
||||
[ 0.38523213 0.13944021 0.64910378 0.7549311 0.90731036 2.48478389
|
||||
1.22697947 1.13771593 0.61908508 1.15238639]
|
||||
[ 1.79328214 0.64910378 3.02162289 3.51425636 4.22359229 11.56684041
|
||||
5.71167406 5.29614612 2.88188373 5.36443813]
|
||||
[ 2.08565179 0.7549311 3.51425636 4.08720685 4.91219011 13.45265242
|
||||
6.64288286 6.15960888 3.35173468 6.23903496]
|
||||
[ 2.50663068 0.90731036 4.22359229 4.91219011 5.90369232 16.16800633
|
||||
7.98371718 7.40289664 4.02826638 7.49835449]
|
||||
[ 6.8647244 2.48478389 11.56684041 13.45265242 16.16800633 44.27812536
|
||||
21.86441684 20.27376652 11.03191576 20.53518988]
|
||||
[ 3.38978208 1.22697947 5.71167406 6.64288286 7.98371718 21.86441684
|
||||
10.79658906 10.01113029 5.44752974 10.14022043]
|
||||
[ 3.14317326 1.13771593 5.29614612 6.15960888 7.40289664 20.27376652
|
||||
10.01113029 9.28281416 5.05121846 9.4025129 ]
|
||||
[ 1.71034931 0.61908508 2.88188373 3.35173468 4.02826638 11.03191576
|
||||
5.44752974 5.05121846 2.748607 5.11635222]
|
||||
[ 3.18370342 1.15238639 5.36443813 6.23903496 7.49835449 20.53518988
|
||||
10.14022043 9.4025129 5.11635222 9.52375513]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1333,15 +1338,15 @@ more practically oriented methods like the blocking technique.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.07625077951488718
|
||||
4.3560752281211315
|
||||
-0.3306482154344632
|
||||
1.1590181727490236 13.220435343291307 24.380661549395565
|
||||
3.788773381830552 4.089069393266692 13.299354039977322
|
||||
[[ 1.15901817 3.78877338 4.08906939]
|
||||
[ 3.78877338 13.22043534 13.29935404]
|
||||
[ 4.08906939 13.29935404 24.38066155]]
|
||||
[34.14195011 0.06190305 4.55626191]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.15035891139512705
|
||||
4.404353162658163
|
||||
0.26135632456837465
|
||||
0.8498535115108263 9.637848274275777 7.478236340866993
|
||||
2.683498103515284 1.8820155508745924 5.929759221040619
|
||||
[[0.84985351 2.6834981 1.88201555]
|
||||
[2.6834981 9.63784827 5.92975922]
|
||||
[1.88201555 5.92975922 7.47823634]]
|
||||
[15.32272016 0.08352309 2.55969487]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1671,7 +1676,7 @@ assumption for approximating <span class="math notranslate nohighlight">\(\sigma
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.007840665517467031 0.9968742237157096
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.030334875296061884 0.9620141923630161
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/statistics_188_1.png" src="_images/statistics_188_1.png" />
|
||||
|
||||
@@ -351,6 +351,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -351,6 +351,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1733,8 +1738,8 @@ developed in the 1970s, namely EISPACK and LINPACK. We describe them shortly he
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[-0.23735423 -0.34348527 -0.45751302 -0.40762065 0.81063784 -1.91668429
|
||||
0.84661055 0.10685672 -0.72237094 0.95928891]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[ 0.85931214 0.24652971 -0.37701519 -0.89783832 -0.42039617 -0.67620794
|
||||
-0.44628307 -1.04740468 -0.04108062 -0.29079591]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1959,26 +1964,26 @@ lowercase letters for vectors and uppercase letters for matrices)</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[0.32314762 0.18808732 0.73055654 0.39680105 0.02304094 0.25217356
|
||||
0.129859 0.64795609 0.64050858 0.41326961]
|
||||
[0.11763276 0.49589995 0.61608406 0.942561 0.42563188 0.26590047
|
||||
0.36366153 0.0110055 0.80283501 0.57112844]
|
||||
[0.17037235 0.25878575 0.66933663 0.4648587 0.32102563 0.28258385
|
||||
0.88952612 0.32433563 0.20378128 0.07772209]
|
||||
[0.4991256 0.9062501 0.68396922 0.53225748 0.50193981 0.70953125
|
||||
0.16772744 0.90167436 0.0375156 0.90055798]
|
||||
[0.39834827 0.10692529 0.48555675 0.24736739 0.42480583 0.13714577
|
||||
0.72496896 0.31602127 0.5101314 0.90050507]
|
||||
[0.9494619 0.45669779 0.1510965 0.06679734 0.5955051 0.08050628
|
||||
0.90783944 0.72596005 0.47331396 0.0422287 ]
|
||||
[0.53851415 0.91315101 0.81556283 0.5664958 0.02538656 0.66160323
|
||||
0.99622734 0.27745486 0.40313394 0.14359337]
|
||||
[0.83853982 0.5523202 0.37501385 0.15553205 0.86789195 0.52184321
|
||||
0.30855785 0.93413623 0.84687351 0.54874291]
|
||||
[0.32402196 0.77986982 0.80692881 0.33091173 0.82391536 0.22779081
|
||||
0.78403064 0.14537136 0.28668988 0.89211729]
|
||||
[0.39499333 0.52319188 0.27585199 0.26939658 0.25115372 0.44987974
|
||||
0.25033611 0.74689928 0.48346049 0.16742049]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[0.95931945 0.57024095 0.91760903 0.39906075 0.08876834 0.0124713
|
||||
0.07144982 0.90842396 0.31617139 0.63909748]
|
||||
[0.52227438 0.89628285 0.96204868 0.34041977 0.11488067 0.27531797
|
||||
0.84740026 0.96646907 0.01508687 0.91848382]
|
||||
[0.17567367 0.55226232 0.73928393 0.68427669 0.13209303 0.91110232
|
||||
0.66357762 0.95798449 0.23780732 0.57013694]
|
||||
[0.39601249 0.53330587 0.06724937 0.34147319 0.64000462 0.24442775
|
||||
0.08281003 0.21557021 0.74700686 0.85155422]
|
||||
[0.61622002 0.92426453 0.66272682 0.30987607 0.01246098 0.31590735
|
||||
0.90414289 0.30579641 0.57699385 0.70800322]
|
||||
[0.39877985 0.76367045 0.85955305 0.74839066 0.92476147 0.77428214
|
||||
0.03819297 0.23549133 0.69784571 0.32911747]
|
||||
[0.87296643 0.7830823 0.17061798 0.7985321 0.73566263 0.0340743
|
||||
0.25628535 0.04001968 0.22513383 0.66806437]
|
||||
[0.14969552 0.72009597 0.07446067 0.06999566 0.91352474 0.87201153
|
||||
0.46028772 0.47205747 0.59014356 0.82634908]
|
||||
[0.29641931 0.78136042 0.27682145 0.1368858 0.42647707 0.952696
|
||||
0.28275928 0.03545828 0.89830971 0.7410929 ]
|
||||
[0.62359412 0.48568753 0.67008686 0.16348056 0.67873521 0.24664656
|
||||
0.32919746 0.43159669 0.25110398 0.02351604]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2033,13 +2038,15 @@ covariance matrix through the <strong>np.linalg.eig()</strong> function.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.15835300124337048
|
||||
3.5560614852167705
|
||||
-0.259533893783188
|
||||
[[0.86807326 2.60292037 1.96983721]
|
||||
[2.60292037 8.73386494 5.86802297]
|
||||
[1.96983721 5.86802297 7.50911947]]
|
||||
[14.78194038 0.0734671 2.25565019]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>-0.22756606771104732
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>3.350239046451652
|
||||
-0.6358520333139864
|
||||
[[ 0.90960239 2.70429053 2.46370204]
|
||||
[ 2.70429053 9.06600773 7.55327382]
|
||||
[ 2.46370204 7.55327382 10.78633152]]
|
||||
[18.29046498 0.08692737 2.38454929]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2264,7 +2271,7 @@ Name: Aragorn, dtype: object
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output traceback highlight-ipythontb notranslate"><div class="highlight"><pre><span></span><span class="gt">---------------------------------------------------------------------------</span>
|
||||
<span class="ne">AttributeError</span><span class="g g-Whitespace"> </span>Traceback (most recent call last)
|
||||
<span class="nn">/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20912/1326197715.py</span> in <span class="ni">?</span><span class="nt">()</span>
|
||||
<span class="nn">/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77069/1326197715.py</span> in <span class="ni">?</span><span class="nt">()</span>
|
||||
<span class="ne">----> </span><span class="mi">6</span> <span class="n">new_hobbit</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'First Name'</span><span class="p">:</span> <span class="p">[</span><span class="s2">"Peregrin"</span><span class="p">],</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">7</span> <span class="s1">'Last Name'</span><span class="p">:</span> <span class="p">[</span><span class="s2">"Took"</span><span class="p">],</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">8</span> <span class="s1">'Place of birth'</span><span class="p">:</span> <span class="p">[</span><span class="s2">"Shire"</span><span class="p">],</span>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1701,7 +1706,7 @@ Since we are not using <strong>Scikit-Learn</strong> here we can define our own
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.9960309859796598
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.9947527587517572
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1718,7 +1723,7 @@ Since we are not using <strong>Scikit-Learn</strong> here we can define our own
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.009724998242604404
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.010439235860004352
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1733,23 +1738,23 @@ Since we are not using <strong>Scikit-Learn</strong> here we can define our own
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[0.04358642 0.01141029 0.0435614 0.00703349 0.05933848 0.04644334
|
||||
0.00355583 0.04946218 0.06473841 0.01522194 0.02492839 0.01331377
|
||||
0.03460821 0.04249722 0.03803121 0.01330851 0.0209366 0.04740225
|
||||
0.01287575 0.02432892 0.0212243 0.02026696 0.01956208 0.06172974
|
||||
0.00781304 0.02535601 0.02299139 0.00642673 0.06636179 0.01543463
|
||||
0.00485699 0.04007138 0.01269131 0.01207585 0.05093545 0.10440237
|
||||
0.05140098 0.04050007 0.00041514 0.01136346 0.01146165 0.00545269
|
||||
0.02308971 0.06033348 0.05777676 0.01621264 0.03982843 0.00664787
|
||||
0.04863731 0.02324012 0.08188888 0.00918064 0.01879279 0.00590621
|
||||
0.01493602 0.02972907 0.02201916 0.01724416 0.00774514 0.02101997
|
||||
0.00960705 0.02180068 0.00078941 0.00684494 0.00135206 0.00448
|
||||
0.02412606 0.00767649 0.10848476 0.00013622 0.04684669 0.03330946
|
||||
0.02565627 0.01196444 0.02901384 0.01765696 0.00550901 0.00408609
|
||||
0.01399696 0.00851785 0.01518425 0.01147217 0.03078393 0.02034322
|
||||
0.03762405 0.07153605 0.00778706 0.02160067 0.00577307 0.02272294
|
||||
0.06726755 0.00914684 0.02512704 0.0452313 0.01120918 0.00652804
|
||||
0.02085067 0.02378634 0.02560435 0.01323492]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[0.0048774 0.03000546 0.01406224 0.05284539 0.04788783 0.02130229
|
||||
0.02623134 0.0312189 0.00828271 0.0333264 0.01039127 0.04606288
|
||||
0.00142296 0.06417796 0.02234126 0.04466842 0.00261107 0.03529826
|
||||
0.03378921 0.0156846 0.02446687 0.00786113 0.06293914 0.01926522
|
||||
0.07425157 0.00050463 0.0262532 0.02488913 0.01273055 0.01047937
|
||||
0.00315702 0.01270269 0.01876257 0.01064438 0.00386265 0.04092917
|
||||
0.00922185 0.09242706 0.0525407 0.00986929 0.02216059 0.01901332
|
||||
0.00896715 0.00402758 0.00442984 0.04099237 0.0017715 0.04160022
|
||||
0.00999576 0.00218856 0.14483777 0.12286595 0.0149996 0.00194921
|
||||
0.00548026 0.01104374 0.00535653 0.05810465 0.0309014 0.00765756
|
||||
0.02954296 0.03077893 0.00995375 0.00133161 0.03530044 0.02867709
|
||||
0.00081442 0.00844629 0.03069367 0.01296443 0.03185121 0.02650658
|
||||
0.02861286 0.00404165 0.11084763 0.01832954 0.00300884 0.01447841
|
||||
0.00247535 0.03531926 0.07316645 0.00458923 0.05633629 0.02054047
|
||||
0.05805861 0.0313967 0.02247131 0.03145864 0.01764364 0.01408861
|
||||
0.035408 0.01927749 0.01439591 0.04600803 0.06175351 0.04317055
|
||||
0.00567929 0.00594615 0.03811479 0.00122361]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1818,15 +1823,15 @@ but now splitting the data into a training set and a test set.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[ 2.014896 -0.32009434 6.3804687 -1.81093622 0.74663164]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[ 1.91347831 1.11445241 1.9118945 2.92213071 -0.82152512]
|
||||
Training R2
|
||||
0.9955259363342327
|
||||
0.9955496867333266
|
||||
Training MSE
|
||||
0.00915723745398148
|
||||
0.009741790670425911
|
||||
Test R2
|
||||
0.9941130198635889
|
||||
0.9962595442701554
|
||||
Test MSE
|
||||
0.009410131112671444
|
||||
0.007025375342852509
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2489,7 +2494,9 @@ the aims is to reproduce Figure 2.11 of <a class="reference external" href="http
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>MSE before scaling: 0.00
|
||||
R2 score before scaling 1.00
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>R2 score before scaling 1.00
|
||||
Feature min values before scaling:
|
||||
[1.00000000e+00 6.97906022e-03 2.43639284e-03 4.87072815e-05
|
||||
1.70037324e-05 5.93601008e-06 3.39931051e-07 1.18670072e-07
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1689,7 +1694,7 @@ theorem.</p>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Bootstrap Statistics :
|
||||
original bias std. error
|
||||
99.9722 14.9105 99.9697 0.149904
|
||||
99.7516 14.8757 99.7508 0.147628
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1936,14 +1941,14 @@ Error: 0.037813671417389005
|
||||
Bias^2: 0.033657685071527665
|
||||
Var: 0.00415598634586135
|
||||
0.037813671417389005 >= 0.033657685071527665 + 0.00415598634586135 = 0.03781367141738902
|
||||
Polynomial degree: 7
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 7
|
||||
Error: 0.02760977349102253
|
||||
Bias^2: 0.022999498260366312
|
||||
Var: 0.004610275230656212
|
||||
0.02760977349102253 >= 0.022999498260366312 + 0.004610275230656212 = 0.027609773491022525
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 8
|
||||
Polynomial degree: 8
|
||||
Error: 0.017355848195593347
|
||||
Bias^2: 0.010331721306655127
|
||||
Var: 0.007024126888938232
|
||||
@@ -1958,14 +1963,14 @@ Error: 0.021592704588025025
|
||||
Bias^2: 0.010516485576645508
|
||||
Var: 0.011076219011379514
|
||||
0.021592704588025025 >= 0.010516485576645508 + 0.011076219011379514 = 0.021592704588025022
|
||||
Polynomial degree: 11
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 11
|
||||
Error: 0.07160048164233104
|
||||
Bias^2: 0.014436800088904942
|
||||
Var: 0.05716368155342608
|
||||
0.07160048164233104 >= 0.014436800088904942 + 0.05716368155342608 = 0.07160048164233102
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Polynomial degree: 12
|
||||
Polynomial degree: 12
|
||||
Error: 0.11547777218872497
|
||||
Bias^2: 0.01628578269596628
|
||||
Var: 0.09919198949275869
|
||||
@@ -2314,29 +2319,31 @@ Mean squared error on test data: 129963.83146596
|
||||
Degree of polynomial: 3
|
||||
Mean squared error on training data: 9054.61775176
|
||||
Mean squared error on test data: 10572.87627342
|
||||
Degree of polynomial: 4
|
||||
Mean squared error on training data: 302.15313054
|
||||
Mean squared error on test data: 433.26292364
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 5
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 4
|
||||
Mean squared error on training data: 302.15313054
|
||||
Mean squared error on test data: 433.26292364
|
||||
Degree of polynomial: 5
|
||||
Mean squared error on training data: 3.64316192
|
||||
Mean squared error on test data: 7.23528337
|
||||
Degree of polynomial: 6
|
||||
Mean squared error on training data: 3.56589683
|
||||
Mean squared error on test data: 10.50427787
|
||||
Degree of polynomial: 7
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 7
|
||||
Mean squared error on training data: 0.47313680
|
||||
Mean squared error on test data: 1.53738247
|
||||
Degree of polynomial: 8
|
||||
Mean squared error on training data: 0.04926746
|
||||
Mean squared error on test data: 0.14629156
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 9
|
||||
Degree of polynomial: 9
|
||||
Mean squared error on training data: 0.02546675
|
||||
Mean squared error on test data: 0.11202337
|
||||
Degree of polynomial: 10
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 10
|
||||
Mean squared error on training data: 0.02424794
|
||||
Mean squared error on test data: 0.22467274
|
||||
Degree of polynomial: 11
|
||||
@@ -2356,29 +2363,31 @@ Mean squared error on test data: 0.28443039
|
||||
Degree of polynomial: 15
|
||||
Mean squared error on training data: 0.00420072
|
||||
Mean squared error on test data: 568.47051432
|
||||
Degree of polynomial: 16
|
||||
Mean squared error on training data: 0.00325450
|
||||
Mean squared error on test data: 48.97630233
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 17
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 16
|
||||
Mean squared error on training data: 0.00325450
|
||||
Mean squared error on test data: 48.97630233
|
||||
Degree of polynomial: 17
|
||||
Mean squared error on training data: 0.00242954
|
||||
Mean squared error on test data: 2.52780600
|
||||
Degree of polynomial: 18
|
||||
Mean squared error on training data: 0.00219195
|
||||
Mean squared error on test data: 429.25695398
|
||||
Degree of polynomial: 19
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 19
|
||||
Mean squared error on training data: 0.00154853
|
||||
Mean squared error on test data: 239.97065359
|
||||
Degree of polynomial: 20
|
||||
Mean squared error on training data: 0.00140846
|
||||
Mean squared error on test data: 1350.24493666
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 21
|
||||
Degree of polynomial: 21
|
||||
Mean squared error on training data: 0.00119688
|
||||
Mean squared error on test data: 1840.50530832
|
||||
Degree of polynomial: 22
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 22
|
||||
Mean squared error on training data: 0.00092898
|
||||
Mean squared error on test data: 1184.60929685
|
||||
Degree of polynomial: 23
|
||||
@@ -2398,23 +2407,23 @@ Mean squared error on test data: 1079.36895644
|
||||
Degree of polynomial: 27
|
||||
Mean squared error on training data: 0.00068091
|
||||
Mean squared error on test data: 3207.25343155
|
||||
Degree of polynomial: 28
|
||||
Mean squared error on training data: 0.00063362
|
||||
Mean squared error on test data: 674.79633065
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 29
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Degree of polynomial: 28
|
||||
Mean squared error on training data: 0.00063362
|
||||
Mean squared error on test data: 674.79633065
|
||||
Degree of polynomial: 29
|
||||
Mean squared error on training data: 0.00063866
|
||||
Mean squared error on test data: 3099.60342978
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20933/626635268.py:73: RuntimeWarning: divide by zero encountered in log10
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77095/626635268.py:73: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(trainingerror), label='Training Error')
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20933/626635268.py:74: RuntimeWarning: divide by zero encountered in log10
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77095/626635268.py:74: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(testerror), label='Test Error')
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week37_148_9.png" src="_images/week37_148_9.png" />
|
||||
<img alt="_images/week37_148_11.png" src="_images/week37_148_11.png" />
|
||||
</div>
|
||||
</div>
|
||||
<p>Note that we kept the intercept column in the fitting here. This means that we need to set the <strong>intercept</strong> in the call to the <strong>Scikit-Learn</strong> function as <strong>False</strong>. Alternatively, we could have set up the design matrix <span class="math notranslate nohighlight">\(X\)</span> without the first column of ones.</p>
|
||||
@@ -2495,7 +2504,7 @@ Mean squared error on test data: 3099.60342978
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20933/3817475779.py:63: RuntimeWarning: divide by zero encountered in log10
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77095/3817475779.py:63: RuntimeWarning: divide by zero encountered in log10
|
||||
plt.plot(polynomial, np.log10(estimated_mse_sklearn), label='Test Error')
|
||||
</pre></div>
|
||||
</div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1832,7 +1837,7 @@ which equals</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x120b67a60>
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x122f46a60>
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week39_82_1.png" src="_images/week39_82_1.png" />
|
||||
@@ -1890,7 +1895,7 @@ which equals</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x1213d5ee0>]
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x123702f40>]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week39_90_1.png" src="_images/week39_90_1.png" />
|
||||
@@ -2184,11 +2189,11 @@ when <span class="math notranslate nohighlight">\(||\nabla_\beta C(\beta_k) || \
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvalues of Hessian Matrix:[0.31492096 4.28033995]
|
||||
[[3.6006178 ]
|
||||
[3.29753883]]
|
||||
[[3.6006178 ]
|
||||
[3.29753883]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvalues of Hessian Matrix:[0.33763884 4.08158332]
|
||||
[[3.77424745]
|
||||
[3.10328867]]
|
||||
[[3.77424745]
|
||||
[3.10328867]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week39_153_1.png" src="_images/week39_153_1.png" />
|
||||
@@ -2219,9 +2224,9 @@ when <span class="math notranslate nohighlight">\(||\nabla_\beta C(\beta_k) || \
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[3.87513212]
|
||||
[3.12510307]]
|
||||
[3.90280702] [3.15433894]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.08279986]
|
||||
[2.951111 ]]
|
||||
[4.11089309] [2.99612864]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2321,11 +2326,11 @@ minimum of this function.</p>
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvalues of Hessian Matrix:[0.28372329 4.0956114 ]
|
||||
[[3.8980893 ]
|
||||
[3.08479726]]
|
||||
[[3.89868561]
|
||||
[3.08425705]]
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Eigenvalues of Hessian Matrix:[0.33983515 4.43295134]
|
||||
[[3.51397199]
|
||||
[3.23805301]]
|
||||
[[3.51348514]
|
||||
[3.23845558]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week39_166_1.png" src="_images/week39_166_1.png" />
|
||||
@@ -2439,7 +2444,7 @@ minimum of this function.</p>
|
||||
>29 f([0.00115631]) = 0.00000
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20948/394505933.py:33: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77123/394505933.py:33: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)
|
||||
print('>%d f(%s) = %.5f' % (i, solution, solution_eval))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2550,7 +2555,7 @@ minimum of this function.</p>
|
||||
>29 f([6.17748881e-07]) = 0.00000
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20948/476849792.py:39: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77123/476849792.py:39: DeprecationWarning: Conversion of an array with ndim > 0 to a scalar is deprecated, and will error in future. Ensure you extract a single element from your array before performing this operation. (Deprecated NumPy 1.25.)
|
||||
print('>%d f(%s) = %.5f' % (i, solution, solution_eval))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3906,16 +3911,16 @@ beta from own Newton code
|
||||
[[4.0586484]
|
||||
[3.0718316]]
|
||||
Eigenvalues of Hessian Matrix:[0.29860173 3.8931686 ]
|
||||
theta from own gd
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own gd
|
||||
[[4.0586484]
|
||||
[3.0718316]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week39_269_1.png" src="_images/week39_269_1.png" />
|
||||
<img alt="_images/week39_269_2.png" src="_images/week39_269_2.png" />
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.02496085]
|
||||
[[4.02496085]
|
||||
[3.12081773]]
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -4004,7 +4009,9 @@ Eigenvalues of Hessian Matrix:[0.27470622 4.24106503]
|
||||
theta from own gd
|
||||
[[3.95906059]
|
||||
[3.02296298]]
|
||||
theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg with momentum
|
||||
[[3.95611042]
|
||||
[2.99475306]]
|
||||
</pre></div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -1334,17 +1339,17 @@ We summarize some of these here for the methods we hvae studied in project one,
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Parameters for OLS using gradient descent
|
||||
[[3.52649344]
|
||||
[4.28384131]
|
||||
[4.39301381]]
|
||||
[[3.76032301]
|
||||
[3.57617159]
|
||||
[4.73446638]]
|
||||
Parameters for Ridge using gradient descent
|
||||
[[3.85580661]
|
||||
[3.22264403]
|
||||
[4.90636879]]
|
||||
[[3.76932996]
|
||||
[3.5039644 ]
|
||||
[4.75712924]]
|
||||
Parameters for Lasso using gradient descent
|
||||
[[3.48209228]
|
||||
[4.41003194]
|
||||
[4.32994479]]
|
||||
[[3.74798782]
|
||||
[3.67690253]
|
||||
[4.66901006]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -1396,11 +1401,11 @@ Parameters for Lasso using gradient descent
|
||||
[[4.]
|
||||
[3.]
|
||||
[5.]]
|
||||
0 [-27.32010544] [-38.1343232]
|
||||
1 [-8.47855119e-14] [-7.94623681e-14]
|
||||
2 [-8.17124146e-16] [-1.01009372e-15]
|
||||
3 [-7.28306304e-16] [-1.47279537e-15]
|
||||
4 [-8.17124146e-16] [-1.01009372e-15]
|
||||
0 [-20.64198317] [-25.87140002]
|
||||
1 [6.95621338e-14] [5.25198941e-14]
|
||||
2 [-3.73034936e-16] [-1.60665948e-16]
|
||||
3 [-1.0658141e-15] [-1.43711157e-15]
|
||||
4 [1.77635684e-17] [-6.65473135e-17]
|
||||
beta from own Newton code
|
||||
[[4.]
|
||||
[3.]
|
||||
@@ -1742,15 +1747,15 @@ function.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[3.97648396]
|
||||
[3.02497282]]
|
||||
Eigenvalues of Hessian Matrix:[0.33604933 4.1740886 ]
|
||||
[[4.13728033]
|
||||
[3.07121643]]
|
||||
Eigenvalues of Hessian Matrix:[0.28247102 4.2443802 ]
|
||||
theta from own gd
|
||||
[[3.97648396]
|
||||
[3.02497282]]
|
||||
[[4.13728033]
|
||||
[3.07121643]]
|
||||
theta from own sdg
|
||||
[[3.93398716]
|
||||
[3.06433206]]
|
||||
[[4.17261945]
|
||||
[3.03589192]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week40_34_1.png" src="_images/week40_34_1.png" />
|
||||
@@ -2464,12 +2469,12 @@ first example shows results with ordinary leats squares.</p>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.12726334]
|
||||
[2.9658822 ]]
|
||||
Eigenvalues of Hessian Matrix:[0.31252573 4.38126738]
|
||||
[[3.80299938]
|
||||
[3.15999738]]
|
||||
Eigenvalues of Hessian Matrix:[0.30207164 4.19150648]
|
||||
theta from own gd
|
||||
[[4.12726334]
|
||||
[2.9658822 ]]
|
||||
[[3.80299938]
|
||||
[3.15999738]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week40_100_1.png" src="_images/week40_100_1.png" />
|
||||
@@ -2540,76 +2545,73 @@ theta from own gd
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.]
|
||||
[3.]]
|
||||
Eigenvalues of Hessian Matrix:[0.28925252 4.30058147]
|
||||
0 [-11.3166934] [-13.25217117]
|
||||
1 [0.05941571] [-0.05123603]
|
||||
2 [0.05541947] [-0.04778995]
|
||||
3 [0.05169202] [-0.04457564]
|
||||
4 [0.04821527] [-0.04157753]
|
||||
5 [0.04497236] [-0.03878107]
|
||||
6 [0.04194757] [-0.0361727]
|
||||
7 [0.03912622] [-0.03373976]
|
||||
8 [0.03649463] [-0.03147046]
|
||||
9 [0.03404004] [-0.02935379]
|
||||
10 [0.03175054] [-0.02737949]
|
||||
11 [0.02961504] [-0.02553797]
|
||||
12 [0.02762316] [-0.02382032]
|
||||
13 [0.02576526] [-0.02221819]
|
||||
14 [0.02403231] [-0.02072382]
|
||||
15 [0.02241593] [-0.01932995]
|
||||
16 [0.02090825] [-0.01802984]
|
||||
17 [0.01950199] [-0.01681717]
|
||||
18 [0.0181903] [-0.01568607]
|
||||
19 [0.01696684] [-0.01463104]
|
||||
20 [0.01582567] [-0.01364697]
|
||||
21 [0.01476125] [-0.01272909]
|
||||
22 [0.01376843] [-0.01187295]
|
||||
23 [0.01284238] [-0.01107438]
|
||||
24 [0.01197861] [-0.01032953]
|
||||
25 [0.01117294] [-0.00963478]
|
||||
26 [0.01042146] [-0.00898675]
|
||||
27 [0.00972053] [-0.00838232]
|
||||
28 [0.00906674] [-0.00781853]
|
||||
29 [0.00845692] [-0.00729266]
|
||||
Eigenvalues of Hessian Matrix:[0.30537749 4.93567389]
|
||||
0 [-12.05438211] [-15.75248147]
|
||||
1 [-0.05121539] [0.03891196]
|
||||
2 [-0.04804662] [0.03650442]
|
||||
3 [-0.0450739] [0.03424583]
|
||||
4 [-0.04228511] [0.03212699]
|
||||
5 [-0.03966887] [0.03013925]
|
||||
6 [-0.0372145] [0.02827449]
|
||||
7 [-0.03491198] [0.0265251]
|
||||
8 [-0.03275192] [0.02488396]
|
||||
9 [-0.03072551] [0.02334435]
|
||||
10 [-0.02882448] [0.0219]
|
||||
11 [-0.02704107] [0.02054501]
|
||||
12 [-0.025368] [0.01927386]
|
||||
13 [-0.02379844] [0.01808136]
|
||||
14 [-0.022326] [0.01696264]
|
||||
15 [-0.02094465] [0.01591314]
|
||||
16 [-0.01964878] [0.01492857]
|
||||
17 [-0.01843308] [0.01400491]
|
||||
18 [-0.0172926] [0.01313841]
|
||||
19 [-0.01622268] [0.01232552]
|
||||
20 [-0.01521896] [0.01156292]
|
||||
21 [-0.01427734] [0.0108475]
|
||||
22 [-0.01339398] [0.01017635]
|
||||
23 [-0.01256527] [0.00954673]
|
||||
24 [-0.01178784] [0.00895606]
|
||||
25 [-0.01105851] [0.00840193]
|
||||
26 [-0.0103743] [0.00788209]
|
||||
27 [-0.00973243] [0.00739441]
|
||||
28 [-0.00913027] [0.00693691]
|
||||
29 [-0.00856537] [0.00650771]
|
||||
theta from own gd
|
||||
[[4.02727068]
|
||||
[2.97648364]]
|
||||
0 [0.00788811] [-0.00680217]
|
||||
1 [0.00735757] [-0.00634466]
|
||||
2 [0.00670354] [-0.00578067]
|
||||
3 [0.00605646] [-0.00522268]
|
||||
4 [0.00545499] [-0.004704]
|
||||
5 [0.00490765] [-0.00423202]
|
||||
6 [0.00441336] [-0.00380578]
|
||||
7 [0.00396824] [-0.00342194]
|
||||
8 [0.0035678] [-0.00307663]
|
||||
9 [0.0032077] [-0.0027661]
|
||||
10 [0.00288393] [-0.0024869]
|
||||
11 [0.00259283]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[-0.00223587]
|
||||
12 [0.0023311] [-0.00201018]
|
||||
13 [0.0020958] [-0.00180727]
|
||||
14 [0.00188425] [-0.00162485]
|
||||
15 [0.00169405] [-0.00146083]
|
||||
16 [0.00152305] [-0.00131337]
|
||||
17 [0.00136931] [-0.0011808]
|
||||
18 [0.00123109] [-0.00106161]
|
||||
19 [0.00110682] [-0.00095445]
|
||||
20 [0.0009951] [-0.00085811]
|
||||
21 [0.00089465] [-0.00077149]
|
||||
22 [0.00080435] [-0.00069361]
|
||||
23 [0.00072315] [-0.0006236]
|
||||
24 [0.00065016] [-0.00056065]
|
||||
25 [0.00058453] [-0.00050406]
|
||||
26 [0.00052553] [-0.00045318]
|
||||
27 [0.00047248] [-0.00040743]
|
||||
28 [0.00042479] [-0.00036631]
|
||||
29 [0.00038191] [-0.00032933]
|
||||
[[3.97368695]
|
||||
[3.01999189]]
|
||||
0 [-0.00803541] [0.00610507]
|
||||
1 [-0.00753825] [0.00572734]
|
||||
2 [-0.0069227] [0.00525966]
|
||||
3 [-0.00630972] [0.00479394]
|
||||
4 [-0.00573543] [0.00435761]
|
||||
5 [-0.00520828] [0.0039571]
|
||||
6 [-0.0047279] [0.00359212]
|
||||
7 [-0.00429126] [0.00326037]
|
||||
8 [-0.00389476] [0.00295912]
|
||||
9 [-0.00353484] [0.00268566]
|
||||
10 [-0.00320815] [0.00243746]
|
||||
11 [-0.00291165] [0.00221219]
|
||||
12 [-0.00264256] [0.00200774]
|
||||
13 [-0.00239833] [0.00182218]
|
||||
14 [-0.00217667] [0.00165377]
|
||||
15 [-0.0019755] [0.00150093]
|
||||
16 [-0.00179292] [0.00136221]
|
||||
17 [-0.00162722] [0.00123631]
|
||||
18 [-0.00147683] [0.00112205]
|
||||
19 [-0.00134034] [0.00101835]
|
||||
20 [-0.00121646] [0.00092423]
|
||||
21 [-0.00110404] [0.00083881]
|
||||
22 [-0.001002] [0.00076129]
|
||||
23 [-0.00090939] [0.00069093]
|
||||
24 [-0.00082535] [0.00062707]
|
||||
25 [-0.00074907] [0.00056912]
|
||||
26 [-0.00067984] [0.00051652]
|
||||
27 [-0.000617] [0.00046878]
|
||||
28 [-0.00055998] [0.00042546]
|
||||
29 [-0.00050823] [0.00038614]
|
||||
theta from own gd wth momentum
|
||||
[[4.00118705]
|
||||
[2.99897637]]
|
||||
[[3.99848956]
|
||||
[3.00114759]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2698,20 +2700,18 @@ theta from own gd wth momentum
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.0673337 ]
|
||||
[3.09000242]]
|
||||
Eigenvalues of Hessian Matrix:[0.26130347 4.78927162]
|
||||
[[3.95706219]
|
||||
[2.94033531]]
|
||||
Eigenvalues of Hessian Matrix:[0.25953954 4.69528374]
|
||||
theta from own gd
|
||||
[[4.0673337 ]
|
||||
[3.09000242]]
|
||||
[[3.95706219]
|
||||
[2.94033531]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week40_104_1.png" src="_images/week40_104_1.png" />
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.05489878]
|
||||
[3.10152451]]
|
||||
[[3.96702819]
|
||||
[2.94477897]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2793,15 +2793,17 @@ theta from own gd
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Own inversion
|
||||
[[4.03339089]
|
||||
[2.92919287]]
|
||||
Eigenvalues of Hessian Matrix:[0.26140984 4.96218268]
|
||||
[[3.85971308]
|
||||
[3.13443492]]
|
||||
Eigenvalues of Hessian Matrix:[0.34481288 4.03344366]
|
||||
theta from own gd
|
||||
[[4.02898102]
|
||||
[2.93257133]]
|
||||
theta from own sdg with momentum
|
||||
[[3.97015949]
|
||||
[2.98377605]]
|
||||
[[3.85978751]
|
||||
[3.13436777]]
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own sdg with momentum
|
||||
[[3.86241466]
|
||||
[3.1395446 ]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2870,9 +2872,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own AdaGrad
|
||||
[[2.00049449]
|
||||
[2.99756956]
|
||||
[4.00250108]]
|
||||
[[2.00000814]
|
||||
[2.99996221]
|
||||
[4.00003533]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -2948,9 +2950,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own RMSprop
|
||||
[[1.99984033]
|
||||
[3.00099032]
|
||||
[3.99898545]]
|
||||
[[2.0000694 ]
|
||||
[2.99939966]
|
||||
[4.00063665]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -3030,9 +3032,9 @@ theta from own sdg with momentum
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>theta from own ADAM
|
||||
[[1.99995089]
|
||||
[3.0002889 ]
|
||||
[3.99971485]]
|
||||
[[1.9999563 ]
|
||||
[3.00054639]
|
||||
[3.999445 ]]
|
||||
</pre></div>
|
||||
</div>
|
||||
</div>
|
||||
@@ -3153,7 +3155,7 @@ It provides composable transformations of Python+NumPy programs: differentiate,
|
||||
return asarray(x, dtype=self.dtype)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x1181696a0>]
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[<matplotlib.lines.Line2D at 0x11f8442e0>]
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week40_120_2.png" src="_images/week40_120_2.png" />
|
||||
@@ -3188,7 +3190,7 @@ It provides composable transformations of Python+NumPy programs: differentiate,
|
||||
</div>
|
||||
</div>
|
||||
<div class="cell_output docutils container">
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><matplotlib.collections.PathCollection at 0x1180defa0>
|
||||
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span><matplotlib.collections.PathCollection at 0x11f812730>
|
||||
</pre></div>
|
||||
</div>
|
||||
<img alt="_images/week40_122_1.png" src="_images/week40_122_1.png" />
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -3396,7 +3401,7 @@ the <em>Hadamard product</em>, meaning element-wise multiplication.</p>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Old accuracy on training data: 0.1440501043841336
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3732,7 +3737,7 @@ Lambda = 10.0
|
||||
Accuracy score on test set: 0.19166666666666668
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3741,7 +3746,7 @@ Lambda = 1e-05
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3750,7 +3755,7 @@ Lambda = 0.0001
|
||||
Accuracy score on test set: 0.08611111111111111
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3759,7 +3764,7 @@ Lambda = 0.001
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -3768,115 +3773,10 @@ Lambda = 0.01
|
||||
Accuracy score on test set: 0.08888888888888889
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77168/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.1
|
||||
Lambda = 0.1
|
||||
Accuracy score on test set: 0.08611111111111111
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.1
|
||||
Lambda = 1.0
|
||||
Accuracy score on test set: 0.08888888888888889
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.1
|
||||
Lambda = 10.0
|
||||
Accuracy score on test set: 0.09166666666666666
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 1e-05
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.0001
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.001
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.01
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.1
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 1.0
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20969/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output traceback highlight-ipythontb notranslate"><div class="highlight"><pre><span></span><span class="gt">---------------------------------------------------------------------------</span>
|
||||
<span class="ne">KeyboardInterrupt</span><span class="g g-Whitespace"> </span>Traceback (most recent call last)
|
||||
<span class="n">Cell</span> <span class="n">In</span><span class="p">[</span><span class="mi">10</span><span class="p">],</span> <span class="n">line</span> <span class="mi">11</span>
|
||||
@@ -3887,18 +3787,10 @@ Accuracy score on test set: 0.10555555555555556
|
||||
<span class="g g-Whitespace"> </span><span class="mi">13</span> <span class="n">DNN_numpy</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="n">dnn</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">15</span> <span class="n">test_predict</span> <span class="o">=</span> <span class="n">dnn</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
|
||||
|
||||
<span class="nn">Cell In[8], line 98,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">95</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="nn">Cell In[8], line 99,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">96</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="ne">---> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
|
||||
<span class="nn">Cell In[8], line 38,</span> in <span class="ni">NeuralNetwork.feed_forward</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">36</span> <span class="k">def</span> <span class="nf">feed_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">37</span> <span class="c1"># feed-forward for training</span>
|
||||
<span class="ne">---> </span><span class="mi">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_h</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">X_data</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_bias</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">39</span> <span class="bp">self</span><span class="o">.</span><span class="n">a_h</span> <span class="o">=</span> <span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">z_h</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_o</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">a_h</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_bias</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="ne">---> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
|
||||
<span class="ne">KeyboardInterrupt</span>:
|
||||
</pre></div>
|
||||
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -2358,7 +2363,7 @@ the <em>Hadamard product</em>, meaning element-wise multiplication.</p>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Old accuracy on training data: 0.1440501043841336
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2694,7 +2699,7 @@ Lambda = 10.0
|
||||
Accuracy score on test set: 0.19166666666666668
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2703,7 +2708,7 @@ Lambda = 1e-05
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2712,7 +2717,7 @@ Lambda = 0.0001
|
||||
Accuracy score on test set: 0.08611111111111111
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2721,7 +2726,7 @@ Lambda = 0.001
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2730,7 +2735,7 @@ Lambda = 0.01
|
||||
Accuracy score on test set: 0.08888888888888889
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
@@ -2739,106 +2744,10 @@ Lambda = 0.1
|
||||
Accuracy score on test set: 0.08611111111111111
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_77180/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.1
|
||||
Lambda = 1.0
|
||||
Accuracy score on test set: 0.08888888888888889
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 0.1
|
||||
Lambda = 10.0
|
||||
Accuracy score on test set: 0.09166666666666666
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 1e-05
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.0001
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.001
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.01
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 0.1
|
||||
Accuracy score on test set: 0.07777777777777778
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Learning rate = 1.0
|
||||
Lambda = 1.0
|
||||
Accuracy score on test set: 0.10555555555555556
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/953065564.py:4: RuntimeWarning: overflow encountered in exp
|
||||
return 1/(1 + np.exp(-x))
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:43: RuntimeWarning: overflow encountered in exp
|
||||
exp_term = np.exp(self.z_o)
|
||||
/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20981/1630775253.py:44: RuntimeWarning: invalid value encountered in divide
|
||||
self.probabilities = exp_term / np.sum(exp_term, axis=1, keepdims=True)
|
||||
</pre></div>
|
||||
</div>
|
||||
<div class="output traceback highlight-ipythontb notranslate"><div class="highlight"><pre><span></span><span class="gt">---------------------------------------------------------------------------</span>
|
||||
<span class="ne">KeyboardInterrupt</span><span class="g g-Whitespace"> </span>Traceback (most recent call last)
|
||||
<span class="n">Cell</span> <span class="n">In</span><span class="p">[</span><span class="mi">8</span><span class="p">],</span> <span class="n">line</span> <span class="mi">11</span>
|
||||
@@ -2849,18 +2758,17 @@ Accuracy score on test set: 0.10555555555555556
|
||||
<span class="g g-Whitespace"> </span><span class="mi">13</span> <span class="n">DNN_numpy</span><span class="p">[</span><span class="n">i</span><span class="p">][</span><span class="n">j</span><span class="p">]</span> <span class="o">=</span> <span class="n">dnn</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">15</span> <span class="n">test_predict</span> <span class="o">=</span> <span class="n">dnn</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">X_test</span><span class="p">)</span>
|
||||
|
||||
<span class="nn">Cell In[6], line 98,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">95</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">X_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="nn">Cell In[6], line 99,</span> in <span class="ni">NeuralNetwork.train</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">96</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">Y_data_full</span><span class="p">[</span><span class="n">chosen_datapoints</span><span class="p">]</span>
|
||||
<span class="ne">---> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">98</span> <span class="bp">self</span><span class="o">.</span><span class="n">feed_forward</span><span class="p">()</span>
|
||||
<span class="ne">---> </span><span class="mi">99</span> <span class="bp">self</span><span class="o">.</span><span class="n">backpropagation</span><span class="p">()</span>
|
||||
|
||||
<span class="nn">Cell In[6], line 38,</span> in <span class="ni">NeuralNetwork.feed_forward</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">36</span> <span class="k">def</span> <span class="nf">feed_forward</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">37</span> <span class="c1"># feed-forward for training</span>
|
||||
<span class="ne">---> </span><span class="mi">38</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_h</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">X_data</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_bias</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">39</span> <span class="bp">self</span><span class="o">.</span><span class="n">a_h</span> <span class="o">=</span> <span class="n">sigmoid</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">z_h</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">41</span> <span class="bp">self</span><span class="o">.</span><span class="n">z_o</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">a_h</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_weights</span><span class="p">)</span> <span class="o">+</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_bias</span>
|
||||
<span class="nn">Cell In[6], line 64,</span> in <span class="ni">NeuralNetwork.backpropagation</span><span class="nt">(self)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">61</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_weights_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">a_h</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">error_output</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">62</span> <span class="bp">self</span><span class="o">.</span><span class="n">output_bias_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">error_output</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="ne">---> </span><span class="mi">64</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_weights_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">matmul</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">X_data</span><span class="o">.</span><span class="n">T</span><span class="p">,</span> <span class="n">error_hidden</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">65</span> <span class="bp">self</span><span class="o">.</span><span class="n">hidden_bias_gradient</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">sum</span><span class="p">(</span><span class="n">error_hidden</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
|
||||
<span class="g g-Whitespace"> </span><span class="mi">67</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">lmbd</span> <span class="o">></span> <span class="mf">0.0</span><span class="p">:</span>
|
||||
|
||||
<span class="ne">KeyboardInterrupt</span>:
|
||||
</pre></div>
|
||||
|
||||
@@ -55,7 +55,7 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
<script defer="defer" src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-mml-chtml.js"></script>
|
||||
<link rel="index" title="Index" href="genindex.html" />
|
||||
<link rel="search" title="Search" href="search.html" />
|
||||
<link rel="next" title="Project 1 on Machine Learning, deadline October 7 (midnight), 2024" href="project1.html" />
|
||||
<link rel="next" title="Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)" href="week45.html" />
|
||||
<link rel="prev" title="Exercises week 43" href="exercisesweek43.html" />
|
||||
<meta name="viewport" content="width=device-width, initial-scale=1" />
|
||||
<meta name="docsearch:language" content="None">
|
||||
@@ -353,6 +353,11 @@ const thebe_selector_output = ".output, .cell_output"
|
||||
Week 44, Convolutional Neural Networks (CNN)
|
||||
</a>
|
||||
</li>
|
||||
<li class="toctree-l1">
|
||||
<a class="reference internal" href="week45.html">
|
||||
Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)
|
||||
</a>
|
||||
</li>
|
||||
</ul>
|
||||
<p aria-level="2" class="caption" role="heading">
|
||||
<span class="caption-text">
|
||||
@@ -5364,10 +5369,10 @@ optimization technique.</p>
|
||||
<p class="prev-next-title">Exercises week 43</p>
|
||||
</div>
|
||||
</a>
|
||||
<a class='right-next' id="next-link" href="project1.html" title="next page">
|
||||
<a class='right-next' id="next-link" href="week45.html" title="next page">
|
||||
<div class="prev-next-info">
|
||||
<p class="prev-next-subtitle">next</p>
|
||||
<p class="prev-next-title">Project 1 on Machine Learning, deadline October 7 (midnight), 2024</p>
|
||||
<p class="prev-next-title">Week 45, Convolutional Neural Networks (CCNs) and Recurrent Neural Networks (RNNs)</p>
|
||||
</div>
|
||||
<i class="fas fa-angle-right"></i>
|
||||
</a>
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because one or more lines are too long
@@ -1077,7 +1077,7 @@
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20753/953065564.py:4: RuntimeWarning: overflow encountered in exp\n",
|
||||
"/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_76811/953065564.py:4: RuntimeWarning: overflow encountered in exp\n",
|
||||
" return 1/(1 + np.exp(-x))\n"
|
||||
]
|
||||
},
|
||||
@@ -1581,84 +1581,6 @@
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 1e-05\n",
|
||||
"Accuracy score on test set: 0.9472222222222222\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 0.0001\n",
|
||||
"Accuracy score on test set: 0.9277777777777778\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 0.001\n",
|
||||
"Accuracy score on test set: 0.9472222222222222\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 0.01\n",
|
||||
"Accuracy score on test set: 0.9305555555555556\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 0.1\n",
|
||||
"Accuracy score on test set: 0.9555555555555556\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 1.0\n",
|
||||
"Accuracy score on test set: 0.7694444444444445\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Learning rate = 0.01\n",
|
||||
"Lambda = 10.0\n",
|
||||
"Accuracy score on test set: 0.19166666666666668\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_20753/953065564.py:4: RuntimeWarning: overflow encountered in exp\n",
|
||||
" return 1/(1 + np.exp(-x))\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"ename": "KeyboardInterrupt",
|
||||
"evalue": "",
|
||||
@@ -1667,8 +1589,8 @@
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[0;32mIn[8], line 11\u001b[0m\n\u001b[1;32m 8\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m j, lmbd \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(lmbd_vals):\n\u001b[1;32m 9\u001b[0m dnn \u001b[38;5;241m=\u001b[39m NeuralNetwork(X_train, Y_train_onehot, eta\u001b[38;5;241m=\u001b[39meta, lmbd\u001b[38;5;241m=\u001b[39mlmbd, epochs\u001b[38;5;241m=\u001b[39mepochs, batch_size\u001b[38;5;241m=\u001b[39mbatch_size,\n\u001b[1;32m 10\u001b[0m n_hidden_neurons\u001b[38;5;241m=\u001b[39mn_hidden_neurons, n_categories\u001b[38;5;241m=\u001b[39mn_categories)\n\u001b[0;32m---> 11\u001b[0m \u001b[43mdnn\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m DNN_numpy[i][j] \u001b[38;5;241m=\u001b[39m dnn\n\u001b[1;32m 15\u001b[0m test_predict \u001b[38;5;241m=\u001b[39m dnn\u001b[38;5;241m.\u001b[39mpredict(X_test)\n",
|
||||
"Cell \u001b[0;32mIn[6], line 99\u001b[0m, in \u001b[0;36mNeuralNetwork.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 96\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mY_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mY_data_full[chosen_datapoints]\n\u001b[1;32m 98\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfeed_forward()\n\u001b[0;32m---> 99\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbackpropagation\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n",
|
||||
"Cell \u001b[0;32mIn[6], line 64\u001b[0m, in \u001b[0;36mNeuralNetwork.backpropagation\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 61\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_weights_gradient \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmatmul(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39ma_h\u001b[38;5;241m.\u001b[39mT, error_output)\n\u001b[1;32m 62\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_bias_gradient \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39msum(error_output, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m)\n\u001b[0;32m---> 64\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhidden_weights_gradient \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmatmul\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mX_data\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mT\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43merror_hidden\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 65\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhidden_bias_gradient \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39msum(error_hidden, axis\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m0\u001b[39m)\n\u001b[1;32m 67\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mlmbd \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m0.0\u001b[39m:\n",
|
||||
"Cell \u001b[0;32mIn[6], line 98\u001b[0m, in \u001b[0;36mNeuralNetwork.train\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 95\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mX_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mX_data_full[chosen_datapoints]\n\u001b[1;32m 96\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mY_data \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mY_data_full[chosen_datapoints]\n\u001b[0;32m---> 98\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfeed_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 99\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbackpropagation()\n",
|
||||
"Cell \u001b[0;32mIn[6], line 38\u001b[0m, in \u001b[0;36mNeuralNetwork.feed_forward\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfeed_forward\u001b[39m(\u001b[38;5;28mself\u001b[39m):\n\u001b[1;32m 37\u001b[0m \u001b[38;5;66;03m# feed-forward for training\u001b[39;00m\n\u001b[0;32m---> 38\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mz_h \u001b[38;5;241m=\u001b[39m \u001b[43mnp\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmatmul\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mX_data\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mhidden_weights\u001b[49m\u001b[43m)\u001b[49m \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mhidden_bias\n\u001b[1;32m 39\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39ma_h \u001b[38;5;241m=\u001b[39m sigmoid(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mz_h)\n\u001b[1;32m 41\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mz_o \u001b[38;5;241m=\u001b[39m np\u001b[38;5;241m.\u001b[39mmatmul(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39ma_h, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_weights) \u001b[38;5;241m+\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput_bias\n",
|
||||
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
|
||||
]
|
||||
}
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 14 KiB After Width: | Height: | Size: 14 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 19 KiB After Width: | Height: | Size: 19 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 23 KiB After Width: | Height: | Size: 25 KiB |
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user