Skip to content

Commit

Permalink
Update course book
Browse files Browse the repository at this point in the history
  • Loading branch information
actions-user committed Jul 16, 2024
1 parent 41c528a commit 782a1f0
Show file tree
Hide file tree
Showing 271 changed files with 3,780 additions and 4,223 deletions.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file not shown.
Binary file not shown.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
Diff not rendered.
679 changes: 173 additions & 506 deletions _sources/projects/ComputerVision/em_synapses.ipynb

Large diffs are not rendered by default.

107 changes: 46 additions & 61 deletions _sources/projects/ComputerVision/spectrogram_analysis.ipynb

Large diffs are not rendered by default.

793 changes: 641 additions & 152 deletions _sources/projects/NaturalLanguageProcessing/sentiment_analysis.ipynb

Large diffs are not rendered by default.

325 changes: 124 additions & 201 deletions _sources/projects/Neuroscience/blurry_vision.ipynb

Large diffs are not rendered by default.

223 changes: 106 additions & 117 deletions _sources/projects/Neuroscience/cellular_segmentation.ipynb

Large diffs are not rendered by default.

489 changes: 108 additions & 381 deletions _sources/projects/ReinforcementLearning/human_rl.ipynb

Large diffs are not rendered by default.

252 changes: 132 additions & 120 deletions _sources/projects/ReinforcementLearning/lunar_lander.ipynb

Large diffs are not rendered by default.

4 changes: 2 additions & 2 deletions projects/ComputerVision/data_augmentation.html
Original file line number Diff line number Diff line change
Expand Up @@ -1763,8 +1763,8 @@ <h2>Cutout<a class="headerlink" href="#cutout" title="Permalink to this heading"
<section id="mixup">
<h2>Mixup<a class="headerlink" href="#mixup" title="Permalink to this heading">#</a></h2>
<p>Mixup is a data augmentation technique that combines pairs of examples via a convex combination of the images and the labels. Given images <span class="math notranslate nohighlight">\(x_i\)</span> and <span class="math notranslate nohighlight">\(x_j\)</span> with labels <span class="math notranslate nohighlight">\(y_i\)</span> and <span class="math notranslate nohighlight">\(y_j\)</span>, respectively, and <span class="math notranslate nohighlight">\(\lambda \in [0, 1]\)</span>, mixup creates a new image <span class="math notranslate nohighlight">\(\hat{x}\)</span> with label <span class="math notranslate nohighlight">\(\hat{y}\)</span> the following way:</p>
<div class="amsmath math notranslate nohighlight" id="equation-a5523f5a-0b64-40da-a805-fd7b38d332ef">
<span class="eqno">(128)<a class="headerlink" href="#equation-a5523f5a-0b64-40da-a805-fd7b38d332ef" title="Permalink to this equation">#</a></span>\[\begin{align}
<div class="amsmath math notranslate nohighlight" id="equation-1585e5df-6a6b-44d4-8d67-9b15997e50a3">
<span class="eqno">(128)<a class="headerlink" href="#equation-1585e5df-6a6b-44d4-8d67-9b15997e50a3" title="Permalink to this equation">#</a></span>\[\begin{align}
\hat{x} &amp;= \lambda x_i + (1 - \lambda) x_j \\
\hat{y} &amp;= \lambda y_i + (1 - \lambda) y_j
\end{align}\]</div>
Expand Down
509 changes: 145 additions & 364 deletions projects/ComputerVision/em_synapses.html

Large diffs are not rendered by default.

70 changes: 28 additions & 42 deletions projects/ComputerVision/spectrogram_analysis.html

Large diffs are not rendered by default.

692 changes: 548 additions & 144 deletions projects/NaturalLanguageProcessing/sentiment_analysis.html

Large diffs are not rendered by default.

102 changes: 50 additions & 52 deletions projects/Neuroscience/blurry_vision.html

Large diffs are not rendered by default.

83 changes: 43 additions & 40 deletions projects/Neuroscience/cellular_segmentation.html

Large diffs are not rendered by default.

407 changes: 54 additions & 353 deletions projects/ReinforcementLearning/human_rl.html

Large diffs are not rendered by default.

194 changes: 115 additions & 79 deletions projects/ReinforcementLearning/lunar_lander.html

Large diffs are not rendered by default.

124 changes: 62 additions & 62 deletions projects/modelingsteps/Example_Deep_Learning_Project.html
Original file line number Diff line number Diff line change
Expand Up @@ -1779,20 +1779,20 @@ <h2>Data ingredients<a class="headerlink" href="#data-ingredients" title="Permal
</div>
</div>
<div class="cell_output docutils container">
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Counter({np.int64(0): 74,
np.int64(1): 74,
np.int64(6): 74,
np.int64(7): 74,
np.int64(8): 74,
np.int64(9): 74,
np.int64(10): 74,
np.int64(11): 74,
np.int64(12): 74,
np.int64(13): 74,
np.int64(4): 73,
np.int64(5): 73,
np.int64(3): 73,
np.int64(2): 73})
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Counter({0: 74,
1: 74,
6: 74,
7: 74,
8: 74,
9: 74,
10: 74,
11: 74,
12: 74,
13: 74,
4: 73,
5: 73,
3: 73,
2: 73})
</pre></div>
</div>
</div>
Expand All @@ -1804,20 +1804,20 @@ <h2>Data ingredients<a class="headerlink" href="#data-ingredients" title="Permal
</div>
</div>
<div class="cell_output docutils container">
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Counter({np.int64(2): 13,
np.int64(3): 13,
np.int64(5): 13,
np.int64(4): 13,
np.int64(6): 12,
np.int64(7): 12,
np.int64(8): 12,
np.int64(9): 12,
np.int64(11): 12,
np.int64(10): 12,
np.int64(12): 12,
np.int64(13): 12,
np.int64(1): 12,
np.int64(0): 12})
<div class="output text_plain highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Counter({2: 13,
3: 13,
5: 13,
4: 13,
6: 12,
7: 12,
8: 12,
9: 12,
11: 12,
10: 12,
12: 12,
13: 12,
1: 12,
0: 12})
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -2067,33 +2067,33 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [100/500], Step [1/2], Loss: 1.0456, Accuracy: 64.15%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [100/500], Step [1/2], Loss: 1.0727, Accuracy: 61.63%
------------------------------------------
Epoch [100/500], Step [2/2], Loss: 0.9540, Accuracy: 64.34%
Epoch [100/500], Step [2/2], Loss: 1.0326, Accuracy: 64.92%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [200/500], Step [1/2], Loss: 0.6982, Accuracy: 75.19%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [200/500], Step [1/2], Loss: 0.8082, Accuracy: 72.09%
------------------------------------------
Epoch [200/500], Step [2/2], Loss: 0.7234, Accuracy: 76.74%
Epoch [200/500], Step [2/2], Loss: 0.8386, Accuracy: 66.67%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [300/500], Step [1/2], Loss: 0.6144, Accuracy: 78.49%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [300/500], Step [1/2], Loss: 0.7040, Accuracy: 74.61%
------------------------------------------
Epoch [300/500], Step [2/2], Loss: 0.6153, Accuracy: 78.29%
Epoch [300/500], Step [2/2], Loss: 0.6436, Accuracy: 77.71%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [400/500], Step [1/2], Loss: 0.4783, Accuracy: 84.69%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [400/500], Step [1/2], Loss: 0.6655, Accuracy: 75.39%
------------------------------------------
Epoch [400/500], Step [2/2], Loss: 0.4215, Accuracy: 87.40%
Epoch [400/500], Step [2/2], Loss: 0.6367, Accuracy: 76.55%
------------------------------------------
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [500/500], Step [1/2], Loss: 0.4122, Accuracy: 87.21%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Epoch [500/500], Step [1/2], Loss: 0.5918, Accuracy: 78.29%
------------------------------------------
Epoch [500/500], Step [2/2], Loss: 0.3677, Accuracy: 86.82%
Epoch [500/500], Step [2/2], Loss: 0.5490, Accuracy: 78.49%
------------------------------------------
</pre></div>
</div>
Expand Down Expand Up @@ -2123,7 +2123,7 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test Accuracy of the model on the 172 test moves: 80.814%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>Test Accuracy of the model on the 172 test moves: 76.163%
</pre></div>
</div>
</div>
Expand All @@ -2137,7 +2137,7 @@ <h2>Build model<a class="headerlink" href="#build-model" title="Permalink to thi
</div>
</div>
<div class="cell_output docutils container">
<img alt="../../_images/1a95bd40d4128913bd4488e76d1f5f5d0bd2f40f980384a709614b82496189bc.png" src="../../_images/1a95bd40d4128913bd4488e76d1f5f5d0bd2f40f980384a709614b82496189bc.png" />
<img alt="../../_images/31ed92e5c2ca3eeaf6cc8b2485430e046e51df5210a5fa7e7bc55e0eda1069cb.png" src="../../_images/31ed92e5c2ca3eeaf6cc8b2485430e046e51df5210a5fa7e7bc55e0eda1069cb.png" />
</div>
</div>
<p>The errors vary each time the model is run, but a common error seems to be that head scratching is predicted from some other movements that also involve arms a lot: throw/catch, hand clapping, phone talking, checking watch, hand waving, taking photo. If we train the model longer, these errors tend to go away as well. For some reason, crossed legged sitting is sometimes misclassified for crawling, but this doesn’t always happen.</p>
Expand Down Expand Up @@ -2225,10 +2225,10 @@ <h1>Step 8: Modeling completion<a class="headerlink" href="#step-8-modeling-comp
</div>
</div>
<div class="cell_output docutils container">
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>74.4186046511628
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>70.34883720930233
</pre></div>
</div>
<img alt="../../_images/1b0939990a6d4358fefacbe6afc306f17de24d2f7ba7598c8b2e37f6e7103e20.png" src="../../_images/1b0939990a6d4358fefacbe6afc306f17de24d2f7ba7598c8b2e37f6e7103e20.png" />
<img alt="../../_images/f779c042380a9a3a46e32f6eada61d9c401d1ed6544b483125122eedaa201a5a.png" src="../../_images/f779c042380a9a3a46e32f6eada61d9c401d1ed6544b483125122eedaa201a5a.png" />
</div>
</div>
<p>That is some pretty good performance based on only 6 / 24 joints!</p>
Expand Down Expand Up @@ -2274,32 +2274,32 @@ <h1>Step 9: Model evaluation<a class="headerlink" href="#step-9-model-evaluation
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>*** FITTING: Left Leg
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 77.33%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 71.51%

*** FITTING: Right Leg
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 72.09%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 76.16%

*** FITTING: Left Arm
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 64.53%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 63.37%

*** FITTING: Right Arm
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 42.44%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 41.28%

*** FITTING: Torso
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 81.98%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 83.14%

*** FITTING: Head
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 53.49%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>limb performance: 51.16%
</pre></div>
</div>
</div>
Expand Down Expand Up @@ -2353,44 +2353,44 @@ <h1>Step 9: Model evaluation<a class="headerlink" href="#step-9-model-evaluation
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>*** FITTING: limbs only
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 82.56%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 66.28%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 84.88%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 53.49%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 68.60%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 71.51%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 56.40%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 85.47%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 84.30%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 67.44%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 82.56%
median performance: 82.56%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 78.49%
median performance: 69.48%

*** FITTING: limbs+torso+head
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 76.74%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 84.88%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 81.40%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 71.51%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 75.00%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 78.49%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 86.63%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 82.56%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 75.00%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 83.14%
</pre></div>
</div>
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 77.91%
median performance: 77.33%
<div class="output stream highlight-myst-ansi notranslate"><div class="highlight"><pre><span></span>performance: 83.14%
median performance: 82.85%
</pre></div>
</div>
</div>
Expand Down
4 changes: 2 additions & 2 deletions projects/modelingsteps/ModelingSteps_10_DL.html

Large diffs are not rendered by default.

16 changes: 8 additions & 8 deletions projects/modelingsteps/ModelingSteps_1through2_DL.html

Large diffs are not rendered by default.

10 changes: 5 additions & 5 deletions projects/modelingsteps/ModelingSteps_3through4_DL.html

Large diffs are not rendered by default.

6 changes: 3 additions & 3 deletions projects/modelingsteps/ModelingSteps_5through6_DL.html

Large diffs are not rendered by default.

8 changes: 4 additions & 4 deletions projects/modelingsteps/ModelingSteps_7through9_DL.html

Large diffs are not rendered by default.

Loading

0 comments on commit 782a1f0

Please sign in to comment.