lars/FYS-STK4155
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
Morten Hjorth-Jensen
2023-11-08 15:57:33 +01:00
parent 2edd177646
commit 3b9f0dbb29
145 changed files with 3873 additions and 2256 deletions
Download Patch File Download Diff File Expand all files Collapse all files
doc/LectureNotes/_build/html/chapteroptimization.html
+32 -22
View File
@@ -343,6 +343,16 @@ const thebe_selector_output = ".output, .cell_output"
Week 43: Deep Learning: Constructing a Neural Network code and solving differential equations
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="week44.html">
Week 44, Convolutional Neural Networks (CNN)
</a>
</li>
<li class="toctree-l1">
<a class="reference internal" href="week45.html">
Week 45, Recurrent Neural Networks
</a>
</li>
</ul>
<p aria-level="2" class="caption" role="heading">
<span class="caption-text">
@@ -1057,11 +1067,11 @@ which equals</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_11016/483257001.py:18: MatplotlibDeprecationWarning: Calling gca() with keyword arguments was deprecated in Matplotlib 3.4. Starting two minor releases later, gca() will take no keyword arguments. The gca() function should only be used to get the current axes, or if no axes exist, create new axes with default keyword arguments. To create a new axes with non-default arguments, use plt.axes() or plt.subplot().
<div class="output stderr highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>/var/folders/td/3yk470mj5p931p9dtkk0y6jw0000gn/T/ipykernel_8738/483257001.py:18: MatplotlibDeprecationWarning: Calling gca() with keyword arguments was deprecated in Matplotlib 3.4. Starting two minor releases later, gca() will take no keyword arguments. The gca() function should only be used to get the current axes, or if no axes exist, create new axes with default keyword arguments. To create a new axes with non-default arguments, use plt.axes() or plt.subplot().
ax = fig.gca(projection=&quot;3d&quot;)
</pre></div>
</div>
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&lt;mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x122d2e790&gt;
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>&lt;mpl_toolkits.mplot3d.art3d.Poly3DCollection at 0x12b1c2700&gt;
</pre></div>
</div>
<img alt="_images/chapteroptimization_61_2.png" src="_images/chapteroptimization_61_2.png" />
@@ -1119,7 +1129,7 @@ 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>[&lt;matplotlib.lines.Line2D at 0x12334c310&gt;]
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[&lt;matplotlib.lines.Line2D at 0x12e9e6280&gt;]
</pre></div>
</div>
<img alt="_images/chapteroptimization_69_1.png" src="_images/chapteroptimization_69_1.png" />
@@ -1376,11 +1386,11 @@ 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>[0.27637358 4.69167569]
[[4.08692465]
[2.84462849]]
[[4.08692465]
[2.84462849]]
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[0.33015882 4.55906894]
[[4.11836068]
[2.85949635]]
[[4.11836068]
[2.85949635]]
</pre></div>
</div>
<img alt="_images/chapteroptimization_123_1.png" src="_images/chapteroptimization_123_1.png" />
@@ -1409,9 +1419,9 @@ 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>[[4.17086577]
[2.92317667]]
[4.14538257] [2.90670236]
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.13451895]
[2.8383548 ]]
[4.19783086] [2.93535577]
</pre></div>
</div>
</div>
@@ -1482,10 +1492,10 @@ C_{\text{ridge}}(\beta) = \frac{1}{n}||X\beta -\mathbf{y}||^2 + \lambda ||\beta|
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.11027723]
[2.92805329]]
[[4.04931542]
[2.97504526]]
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[[4.12575322]
[2.87918262]]
[[4.08876865]
[2.90510842]]
</pre></div>
</div>
<img alt="_images/chapteroptimization_132_1.png" src="_images/chapteroptimization_132_1.png" />
@@ -1735,15 +1745,15 @@ 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
[[3.22532324]
[3.44210664]]
Eigenvalues of Hessian Matrix:[0.30012384 4.62464344]
[[3.78515112]
[3.19029687]]
Eigenvalues of Hessian Matrix:[0.30739146 4.15768662]
theta from own gd
[[3.22532324]
[3.44210664]]
[[3.78515112]
[3.19029687]]
theta from own sdg
[[3.17736035]
[3.48289037]]
[[3.81425332]
[3.25285802]]
</pre></div>
</div>
<img alt="_images/chapteroptimization_148_1.png" src="_images/chapteroptimization_148_1.png" />