added video

This commit is contained in:
Morten Hjorth-Jensen
2024-08-27 15:21:48 +02:00
parent b632f7ea45
commit e0b90b192c
9 changed files with 1301 additions and 1300 deletions
File diff suppressed because it is too large Load Diff
File diff suppressed because one or more lines are too long
+28 -33
View File
@@ -1118,6 +1118,7 @@ doconce format html week35.do.txt --no_mako -->
<ol class="simple">
<li><p>These lecture notes</p></li>
<li><p><a class="reference external" href="https://youtu.be/VKakN-e4aUA">Video of lecture</a></p></li>
<li><p><a class="reference external" href="https://youtu.be/yiY0OltU1s8">Video for exercises week 35</a></p></li>
<li><p>Goodfellow, Bengio and Courville, Deep Learning, chapter 2 on linear algebra and sections 3.1-3.10 on elements of statistics (background)</p></li>
<li><p>Raschka et al on preprocessing of data, relevant for exercise 3 this week, see chapter 4.</p></li>
<li><p>For exercise 1 of week 35, the book by A. Aldo Faisal, Cheng Soon Ong, and Marc Peter Deisenroth on the Mathematics of Machine Learning, may be very relevant. In particular chapter 5 at URL”<a class="reference external" href="https://mml-book.github.io/">https://mml-book.github.io/</a>” (section 5.5 on derivatives) is very useful for exercise 1 this coming week.</p></li>
@@ -1597,7 +1598,7 @@ 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>0.9960987015666213
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.9955853547770925
</pre></div>
</div>
</div>
@@ -1614,7 +1615,7 @@ 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>0.008479177639949449
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>0.009975924157146357
</pre></div>
</div>
</div>
@@ -1629,31 +1630,23 @@ 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>[3.33897624e-02 2.82933065e-02 2.08502578e-02 5.70368882e-03
1.36392181e-02 3.54890204e-02 4.52322923e-02 7.20183951e-02
6.08424143e-03 1.51876722e-02 2.72107224e-02 4.38536455e-02
1.01890271e-02 7.59583924e-03 1.54362677e-02 1.39857639e-02
3.04600349e-02 5.35392690e-02 6.14211764e-03 2.44308477e-03
1.74218636e-03 1.36163844e-02 3.15915417e-02 6.07182377e-04
5.90558936e-03 5.35227195e-05 9.78647442e-03 1.26624586e-02
1.45101677e-02 1.92012445e-02 5.05837221e-02 6.17112259e-03
1.11723198e-02 6.93356993e-03 1.93438490e-02 1.33978089e-02
7.08793873e-03 2.86963555e-02 3.74845516e-02 9.09026386e-03
9.83959386e-03 1.47179272e-02 2.28687236e-03 1.79501684e-02
4.29334886e-02 5.70888990e-03 1.77605945e-03 8.68241292e-03
9.19704684e-02 1.94558442e-02 6.13073296e-03 4.87955713e-03
2.61004589e-02 2.48914361e-02 1.68762810e-02 5.66037582e-02
3.32605607e-02 2.20330004e-02 8.80858500e-02 5.40907614e-02
6.99537250e-03 2.13619518e-02 2.92595981e-02 2.13400535e-02
4.74734301e-03 7.13396439e-03 2.94193224e-03 1.28749016e-02
1.04702436e-01 2.25969618e-02 4.31600436e-03 4.04787888e-02
7.73538998e-03 2.21569425e-02 1.89182406e-02 1.89215419e-03
1.06170091e-02 1.90932454e-02 1.33876558e-02 9.18004907e-03
3.59120619e-02 4.23663774e-03 4.75744838e-02 5.05958988e-03
7.91845464e-04 3.83995681e-02 1.29557246e-02 4.35758612e-02
3.74194699e-03 2.05752451e-02 1.29311961e-02 7.07147609e-03
5.43495641e-03 9.07930457e-03 9.59668773e-04 2.80566926e-03
3.14738036e-02 1.34254673e-02 4.80114766e-02 5.31124303e-02]
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[0.03310948 0.03502605 0.01238528 0.01145325 0.01120753 0.04024121
0.02365946 0.00802057 0.01686313 0.06417556 0.02459689 0.03750064
0.00027126 0.04470158 0.02703163 0.07640212 0.0372278 0.12977735
0.00607227 0.05519101 0.00506541 0.01080061 0.01466418 0.0235557
0.0039114 0.01903413 0.00530754 0.00284682 0.00234831 0.00575843
0.00288898 0.00864249 0.03421216 0.0238318 0.02846355 0.05133809
0.02410477 0.00618364 0.00616064 0.05455225 0.01761095 0.00756235
0.02465031 0.01140481 0.00569631 0.04057615 0.0102482 0.06849452
0.02568311 0.0038013 0.02460166 0.00968573 0.00510049 0.03368503
0.0275728 0.01629911 0.03063595 0.00953303 0.04675468 0.04944357
0.00768229 0.00974873 0.02744664 0.0039037 0.02755583 0.00960513
0.00340126 0.02270334 0.03343177 0.01023188 0.01071707 0.0053717
0.00989298 0.02147188 0.01733341 0.02393489 0.09413086 0.00693229
0.01547395 0.00893513 0.01198614 0.00880861 0.05151828 0.01074123
0.02611675 0.04174576 0.02879514 0.04182729 0.05830426 0.02412449
0.03064238 0.00449104 0.02332052 0.04607275 0.06390074 0.02795048
0.0056416 0.00463706 0.0240445 0.02081809]
</pre></div>
</div>
</div>
@@ -1722,15 +1715,15 @@ 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>[ 1.9493303 0.64347371 2.56535839 3.65129524 -1.82028236]
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>[ 1.90133797 0.41151358 5.10853105 -1.67354637 1.25212002]
Training R2
0.9968948714928851
0.9943899533894374
Training MSE
0.007373820933373729
0.012961500458019132
Test R2
0.9971066204281798
0.9940852985232707
Test MSE
0.009252005542369688
0.012176386103148444
</pre></div>
</div>
</div>
@@ -2411,7 +2404,9 @@ Feature min values after scaling:
-0.88613493 -0.884669 -0.88323026 -0.88182591 -0.75269037 -0.75050135
-0.74829661 -0.74607851 -0.74384949 -0.6652177 -0.66294408 -0.66064822
-0.65833132 -0.65599456 -0.6536392 ]
Feature max values after scaling:
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Feature max values after scaling:
[0. 1.71737253 1.75576555 2.20916295 2.23971032 2.26995402
2.60543038 2.63162342 2.65743689 2.68286725 2.94273542 2.96631321
2.98947894 3.01222822 3.034557 3.24159785 3.26297455 3.28391978