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 20, 2024
1 parent 5c1b3fc commit a40180d
Show file tree
Hide file tree
Showing 216 changed files with 28,383 additions and 29,995 deletions.
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.
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.
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.
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.
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.
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.
Original file line number Diff line number Diff line change
Expand Up @@ -38,8 +38,5 @@ I’m a student, how can I make the most out of my mentoring experience?

**Keep a respectful conversation**: mentoring is a social interaction. You may construct a long-lasting relationship with your mentor and your peers. Thus, be kind and have fun, as you’ll be discussing your dreams and career goals, as well as the efforts you’ve made so far to follow them.

---

# Find additional Professional Development resources through our website

https://neuromatch.io/resources/
**Find additional Professional Development resources through [our website](https://neuromatch.io/resources/)**
2 changes: 1 addition & 1 deletion _sources/tutorials/Schedule/daily_schedules.md
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,7 @@ Closing Ceremony/Graduation: We will do this all together on crowdcast.
| 4:25-4:45 | Break |
| 4:45-5:15\** | Course Review & Feedback |
| 5:15-5:30\** | Pod farewell |
| 5:30-6:15\** | Closing Ceremony/Graduation |
| 6:30-7:15\** | Closing Ceremony/Graduation |

\* : This is the last hour and a quarter of projects time for slot 3

Expand Down
23 changes: 10 additions & 13 deletions _sources/tutorials/W1D2_ComparingTasks/student/W1D2_Tutorial1.ipynb
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,6 @@
"2. Train a network to accomplish these tasks and compare the performance of these networks.\n",
"3. Measure how well different representations generalize\n",
"\n",
"**Important note**: this tutorial leverages GPU acceleration. Using a GPU runtime in colab will make the the tutorial run 10x faster.\n",
"\n",
"Let's get started.\n"
]
},
Expand Down Expand Up @@ -1483,8 +1481,8 @@
" for batch_idx, (X, y) in enumerate(sampled_val_loader):\n",
" predictions = model(X)\n",
" _, predicted_classes = torch.max(predictions, 1)\n",
" all_preds.extend(predicted_classes.cpu().numpy())\n",
" all_labels.extend(y.cpu().numpy())\n",
" all_preds.extend(predicted_classes.numpy())\n",
" all_labels.extend(y.numpy())\n",
"\n",
" #Compute confusion matrix\n",
" conf_matrix = confusion_matrix(all_labels, all_preds)\n",
Expand Down Expand Up @@ -1566,7 +1564,7 @@
"execution": {}
},
"source": [
"[*Click for solution*](https://github.com/neuromatch/NeuroAI_Course/tree/main/tutorials/W1D2_ComparingTasks/solutions/W1D2_Tutorial1_Solution_28d9d52f.py)\n",
"[*Click for solution*](https://github.com/neuromatch/NeuroAI_Course/tree/main/tutorials/W1D2_ComparingTasks/solutions/W1D2_Tutorial1_Solution_17513eb4.py)\n",
"\n"
]
},
Expand Down Expand Up @@ -1601,11 +1599,11 @@
"source": [
"## Section 1.2: Regression\n",
"\n",
"After examining the use of network architecture for digit classification, we now transition to a regression task using the same architecture. We are going to pick a very simple output task, which is not directly related to classification or the identify of the digits. In this task, given an image of a handwritten digit, our objective is to predict the number of pixels that are 'ON' (i.e., pixel values greater than 0.5). This can be achieved with the network performing operations similar to a simple addition of the pixels (though it might still take time and data for the network to find this simple solution). Thus, we don't expect that the network will learn rich representations that are useful for other tasks such as classification.\n",
"After examining the use of network architecture for digit classification, we now transition to a regression task using the same architecture. We are going to pick a very simple output task that is not directly related to the classification or the identification of the digits. In this task, given an image of a handwritten digit, our objective is to predict the number of pixels that are 'ON' (i.e., pixel values greater than 0.5). This can be achieved by the network performing operations similar to the simple addition of pixels (though it might still take time and data for the network to find this simple solution). Thus, we don't expect that the network will learn rich representations that are useful for other tasks, such as classification.\n",
"\n",
"### Task objective\n",
"\n",
"This regression task, while relatively simple as it involves summing pixel values, serves to illustrate how well a Convolutional Neural Network (CNN) can adapt to learning a continuous output instead of discrete class labels. Note that we'll regress the normalized \n",
"This regression task, while relatively simple as it involves summing pixel values, serves to illustrate how well a Convolutional Neural Network (CNN) can adapt to learning a continuous output instead of discrete class labels. Note that we'll regress the normalized images.\n",
"\n",
"### Output layer\n",
"\n",
Expand Down Expand Up @@ -1659,8 +1657,7 @@
"\n",
"- $N$ is the number of samples\n",
"- $y_i$ is the true label for the $i^{th}$ sample, the number of on pixels\n",
"- $\\mu_i = \\text{CNN}(x_i)$ is the output of the model for the $i^{th}$ sample\n",
"- $f$ is the ReLU activation function"
"- $\\mu_i = \\text{CNN}(x_i)$ is the output of the model for the $i^{th}$ sample"
]
},
{
Expand Down Expand Up @@ -2251,9 +2248,9 @@
" for batch_idx, (X, _) in enumerate(sampled_val_loader):\n",
" if batch_idx == 0:\n",
" outputs = model(X)\n",
" orig = X.cpu().numpy()\n",
" orig = X.numpy()\n",
" original_images.extend(orig)\n",
" recon = outputs.cpu().numpy()\n",
" recon = outputs.numpy()\n",
" reconstructed_images.extend(recon)\n",
" plot_reconstructions(original_images, reconstructed_images, N_train_data, epochs_max_autoencoder)\n",
" break\n",
Expand Down Expand Up @@ -2602,9 +2599,9 @@
" for batch_idx, (X, _) in enumerate(sampled_val_loader):\n",
" if batch_idx == 0: # Only visualize the first batch for simplicity\n",
" outputs = model(X)\n",
" orig = X.cpu().numpy()\n",
" orig = X.numpy()\n",
" original_images.extend(orig)\n",
" recon = outputs.cpu().numpy()\n",
" recon = outputs.numpy()\n",
" reconstructed_images.extend(recon)\n",
" fig = plt.figure(figsize=(8, 4))\n",
" rows, cols = 2, 6\n",
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -343,7 +343,7 @@
"\n",
" rdms_comp = rsatoolbox.rdm.compare(rdms, rdms, method=rdm_comp_method)\n",
" if rdm_comp_method == 'cosine':\n",
" rdms_comp = 1 - rdms_comp\n",
" rdms_comp = np.arccos(rdms_comp)\n",
" rdms_comp = np.nan_to_num(rdms_comp, nan=0.0)\n",
"\n",
" # Symmetrize\n",
Expand Down Expand Up @@ -1409,9 +1409,7 @@
"\n",
"$$\\hat M(\\text{layer i}, \\text{image j x image k})$$\n",
"\n",
"We can then calculate the distances between the different rows of this new matrix. This new measure captures the distances between representational geometries of different layers. So we are now creating an RDM matrix of the RDM matrices!\n",
"\n",
"We compute the similarity between geometries using the cosine dissimilarity. The resulting matrix has the dimensions of `#layers` by `#layers`.\n",
"We can then calculate the cosine similarity between the different rows of this new matrix. By taking the arccos of this measure, we obtain a proper distance between representational geometries of different layers (Williams et al. 2021). So, we are now creating an RDM matrix of the RDM matrices! The resulting matrix has the dimensions of `#layers` by `#layers`.\n",
"\n",
"The last step to visualize the path is to embed the distances between the geometries in a lower dimensional space. We use MDS to reduce the dimensions to 2 in order to show each computational step as a point in a 2D space."
]
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -932,7 +932,7 @@
"\n",
"\n",
"### How can we quantify sparsity?\n",
"- **$\\ell_0$ pseudo-norm** -- the count of non-zero values: $\\|\\mathbf{x}\\|_{\\ell_0}=\\sum_i \\mathbb{1}_{x_i=0}$ where $\\mathbb{1}$ is an indicator function equal to 1 if and only if the argument is true. This is more difficult to work with than other proxy measures that are convex or differentiable.\n",
"- **$\\ell_0$ pseudo-norm** -- the count of non-zero values: $\\|\\mathbf{x}\\|_{\\ell_0}=\\sum_i \\mathbb{1}_{x_i\\neq0}$ where $\\mathbb{1}$ is an indicator function equal to 1 if and only if the argument is true. This is more difficult to work with than other proxy measures that are convex or differentiable.\n",
"\n",
"- **$\\ell_1$ norm** -- the sum of the absolute values: $\\|\\mathbf{x}\\|_{\\ell_1}=\\sum_i |x_i|$\n",
"\n",
Expand Down
2 changes: 1 addition & 1 deletion _sources/tutorials/W2D1_Macrocircuits/further_reading.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,4 +13,4 @@

## Tutorial 3: Modularity

- [Inductive biases of neural networks for generalization in spatial navigation](https://www.biorxiv.org/content/10.1101/2022.12.07.519515v1)
- [Inductive biases of neural network modularity in spatial navigation](https://www.science.org/doi/10.1126/sciadv.adk1256)
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@
"4. Use neural decoding to understand why the modular architecture for this specific task is advantageous.\n",
"5. Keep the No-Free-Lunch Theorem in mind: the benefits of a modular architecture for one task cannot apply to all possible tasks.\n",
"\n",
"This tutorial is based on this [paper](https://www.biorxiv.org/content/10.1101/2022.12.07.519515v2.abstract)."
"This tutorial is based on this [paper](https://www.science.org/doi/10.1126/sciadv.adk1256)."
]
},
{
Expand Down Expand Up @@ -3501,7 +3501,7 @@
"---\n",
"# Bonus Section 2: Generalization, but no free lunch\n",
"\n",
"The No Free Lunch theorems proved that no inductive bias can excel across all tasks. It has been studied in the [paper](https://www.biorxiv.org/content/10.1101/2022.12.07.519515v2.abstract) that agents with a modular architecture can acquire the underlying structure of the training task. In contrast, holistic agents tend to acquire different knowledge than modular agents during training, such as forming beliefs based on unreliable information sources or exhibiting less efficient control actions. The novel gain task has a structure similar to the training task, consequently, a modular agent that accurately learns the training task's structure can leverage its knowledge in these novel tasks.\n",
"The No Free Lunch theorems proved that no inductive bias can excel across all tasks. It has been studied in the [paper](https://www.science.org/doi/10.1126/sciadv.adk1256) that agents with a modular architecture can acquire the underlying structure of the training task. In contrast, holistic agents tend to acquire different knowledge than modular agents during training, such as forming beliefs based on unreliable information sources or exhibiting less efficient control actions. The novel gain task has a structure similar to the training task, consequently, a modular agent that accurately learns the training task's structure can leverage its knowledge in these novel tasks.\n",
"\n",
"However, it is worth noting that an infinite number of new tasks can be constructed, diverging from the training task's structure but aligning with the 'inferior' beliefs and control acquired by holistic agents.\n",
"\n",
Expand Down
1 change: 0 additions & 1 deletion genindex.html
Original file line number Diff line number Diff line change
Expand Up @@ -846,7 +846,6 @@
<li class="toctree-l1"><a class="reference internal" href="projects/professional_development/README.html">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="projects/professional_development/mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
1 change: 0 additions & 1 deletion prereqs/NeuroAI.html
Original file line number Diff line number Diff line change
Expand Up @@ -853,7 +853,6 @@
<li class="toctree-l1"><a class="reference internal" href="../projects/professional_development/README.html">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../projects/professional_development/mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
1 change: 0 additions & 1 deletion projects/README.html
Original file line number Diff line number Diff line change
Expand Up @@ -849,7 +849,6 @@
<li class="toctree-l1"><a class="reference internal" href="professional_development/README.html">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="professional_development/mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
1 change: 0 additions & 1 deletion projects/docs/datasets_overview.html
Original file line number Diff line number Diff line change
Expand Up @@ -849,7 +849,6 @@
<li class="toctree-l1"><a class="reference internal" href="../professional_development/README.html">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../professional_development/mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
1 change: 0 additions & 1 deletion projects/docs/project_guidance.html
Original file line number Diff line number Diff line change
Expand Up @@ -853,7 +853,6 @@
<li class="toctree-l1"><a class="reference internal" href="../professional_development/README.html">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="../professional_development/mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
1 change: 0 additions & 1 deletion projects/professional_development/README.html
Original file line number Diff line number Diff line change
Expand Up @@ -853,7 +853,6 @@
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Introduction</a></li>
<li class="toctree-l1"><a class="reference internal" href="mentorship_program.html">Mentorship Program</a></li>


</ul>

</div>
Expand Down
17 changes: 1 addition & 16 deletions projects/professional_development/mentorship_program.html
Original file line number Diff line number Diff line change
Expand Up @@ -852,7 +852,6 @@
<li class="toctree-l1"><a class="reference internal" href="README.html">Introduction</a></li>
<li class="toctree-l1 current active"><a class="current reference internal" href="#">Mentorship Program</a></li>


</ul>

</div>
Expand Down Expand Up @@ -1016,11 +1015,6 @@ <h2> Contents </h2>
Useful tips for Students
</a>
</li>
<li class="toc-h1 nav-item toc-entry">
<a class="reference internal nav-link" href="#find-additional-professional-development-resources-through-our-website">
Find additional Professional Development resources through our website
</a>
</li>
</ul>

</nav>
Expand Down Expand Up @@ -1059,11 +1053,7 @@ <h1>Useful tips for Students<a class="headerlink" href="#useful-tips-for-student
<p><strong>Take notes and work hard</strong>: take notes during or after the meeting to save what has been said. Try to elaborate and work on the suggestions you received so that when you meet up again, you can provide some advances to your mentor and peers.</p>
<p><strong>Own your actions</strong>: a mentor is there to guide you, but not to solve your problems. Help might come just as verbal advice. In other cases, they might give you resources like books, papers or institutes to contact. Don’t be afraid to ask, but in the end, you must take action based on this advice, your interests, and your capabilities.</p>
<p><strong>Keep a respectful conversation</strong>: mentoring is a social interaction. You may construct a long-lasting relationship with your mentor and your peers. Thus, be kind and have fun, as you’ll be discussing your dreams and career goals, as well as the efforts you’ve made so far to follow them.</p>
</section>
<hr class="docutils" />
<section class="tex2jax_ignore mathjax_ignore" id="find-additional-professional-development-resources-through-our-website">
<h1>Find additional Professional Development resources through our website<a class="headerlink" href="#find-additional-professional-development-resources-through-our-website" title="Permalink to this heading">#</a></h1>
<p>https://neuromatch.io/resources/</p>
<p><strong>Find additional Professional Development resources through <a class="reference external" href="https://neuromatch.io/resources/">our website</a></strong></p>
</section>

<script type="text/x-thebe-config">
Expand Down Expand Up @@ -1127,11 +1117,6 @@ <h1>Find additional Professional Development resources through our website<a cla
Useful tips for Students
</a>
</li>
<li class="toc-h1 nav-item toc-entry">
<a class="reference internal nav-link" href="#find-additional-professional-development-resources-through-our-website">
Find additional Professional Development resources through our website
</a>
</li>
</ul>

</nav>
Expand Down
Loading

0 comments on commit a40180d

Please sign in to comment.