week 1

Author: mhjensen

doc/pub/week1/html/week1-bs.html

@@ -83,10 +83,10 @@
                2,
                None,
                'good-books-with-hands-on-material-and-codes'),
-              ('Twst yourself: Deep learning 1',
+              ('Test yourself: Deep learning 1',
                2,
                None,
-               'twst-yourself-deep-learning-1'),
+               'test-yourself-deep-learning-1'),
               ('Test yourself: Deep learning 2',
                2,
                None,
@@ -376,7 +376,7 @@
      <!-- navigation toc: --> <li><a href="#gaussian-processes-and-bayesian-analysis" style="font-size: 80%;">Gaussian processes and Bayesian analysis</a></li>
      <!-- navigation toc: --> <li><a href="#hpc-path" style="font-size: 80%;">HPC path</a></li>
      <!-- navigation toc: --> <li><a href="#good-books-with-hands-on-material-and-codes" style="font-size: 80%;">Good books with hands-on material and codes</a></li>
-     <!-- navigation toc: --> <li><a href="#twst-yourself-deep-learning-1" style="font-size: 80%;">Twst yourself: Deep learning 1</a></li>
+     <!-- navigation toc: --> <li><a href="#test-yourself-deep-learning-1" style="font-size: 80%;">Test yourself: Deep learning 1</a></li>
      <!-- navigation toc: --> <li><a href="#test-yourself-deep-learning-2" style="font-size: 80%;">Test yourself: Deep learning 2</a></li>
      <!-- navigation toc: --> <li><a href="#test-yourself-optimization-part" style="font-size: 80%;">Test yourself: Optimization part</a></li>
      <!-- navigation toc: --> <li><a href="#test-yourself-analysis-of-results" style="font-size: 80%;">Test yourself: Analysis of results</a></li>
@@ -491,12 +491,12 @@ <h2 id="overview-of-first-week-january-19-23-2026" class="anchor">Overview of fi
 <div class="panel-body">
 <!-- subsequent paragraphs come in larger fonts, so start with a paragraph -->
 <ol>
- <li> Presentation of course</li>
- <li> Discussion of possible projects</li>
- <li> Deep learning methods, mathematics and  review of neural networks
+<li> Presentation of course</li>
+<li> Discussion of possible projects</li>
+<li> Deep learning methods, mathematics and  review of neural networks
 <!-- o "Video of lecture at <a href="https://youtu.be/SY57dC46L9o" target="_self"><tt>https://youtu.be/SY57dC46L9o</tt></a> --></li>
- <li> Recommended reading first three weeks: Raschka et al chapter 11 and Goodfellow et al chapters 6 and 7</li>
- <li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_self"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
+<li> Recommended reading first three weeks: Raschka et al chapters 11-12 and Goodfellow et al chapters 6-8</li>
+<li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_self"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
 </ol>
 </div>
 </div>
@@ -564,6 +564,8 @@ <h2 id="additional-topics-kernel-regression-gaussian-processes-and-bayesian-stat
 variable).
 </p>
 
+<p>These topics are not covered by the lectures but can be used to define projects.</p>
+
 <!-- !split -->
 <h2 id="project-paths-overarching-view" class="anchor">Project paths, overarching view </h2>
 
@@ -671,14 +673,18 @@ <h2 id="good-books-with-hands-on-material-and-codes" class="anchor">Good books w
 </p>
 
 <!-- !split -->
-<h2 id="twst-yourself-deep-learning-1" class="anchor">Twst yourself: Deep learning 1  </h2>
+<h2 id="test-yourself-deep-learning-1" class="anchor">Test yourself: Deep learning 1  </h2>
+
+<p>Deep learning (essentially neural networks)
+background knowledge we deem important to be familiar with.
+</p>
 
 <ol>
-<li> Describe the architecture of a typical feed forward  Neural Network (NN).</li> 
+<li> Can you describe the architecture of a typical feed forward  Neural Network (NN).</li> 
 <li> What is an activation function and discuss the use of an activation function.</li>
 <li> Can you name and explain three different types of activation functions?</li>
 <li> You are using a deep neural network for a prediction task. After training your model, you notice that it is strongly overfitting the training set and that the performance on the test isn&#8217;t good. What can you do to reduce overfitting?</li>
-<li> How would you know if your model is suffering from the problem of exploding Gradients?</li>
+<li> How would you know if your model is suffering from the problem of exploding gradients?</li>
 <li> Can you name and explain a few hyperparameters used for training a neural network?</li>
 </ol>
 <!-- !split -->
@@ -1960,7 +1966,7 @@ <h2 id="updating-the-gradients" class="anchor">Updating the gradients  </h2>
 </footer>
 -->
 <center style="font-size:80%">
-<!-- copyright --> &copy; 1999-2025, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+<!-- copyright --> &copy; 1999-2026, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
 </center>
 </body>
 </html>

doc/pub/week1/html/week1-reveal.html

@@ -187,7 +187,7 @@ <h4>January 22, 2026</h4>
 
 
 <center style="font-size:80%">
-<!-- copyright --> &copy; 1999-2025, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+<!-- copyright --> &copy; 1999-2026, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
 </center>
 </section>
 
@@ -198,12 +198,12 @@ <h2 id="overview-of-first-week-january-19-23-2026">Overview of first week, Janua
 <b></b>
 <p>
 <ol>
- <p><li> Presentation of course</li>
- <p><li> Discussion of possible projects</li>
- <p><li> Deep learning methods, mathematics and  review of neural networks
+<p><li> Presentation of course</li>
+<p><li> Discussion of possible projects</li>
+<p><li> Deep learning methods, mathematics and  review of neural networks
 <!-- o "Video of lecture at <a href="https://youtu.be/SY57dC46L9o" target="_blank"><tt>https://youtu.be/SY57dC46L9o</tt></a> --></li>
- <p><li> Recommended reading first three weeks: Raschka et al chapter 11 and Goodfellow et al chapters 6 and 7</li>
- <p><li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
+<p><li> Recommended reading first three weeks: Raschka et al chapters 11-12 and Goodfellow et al chapters 6-8</li>
+<p><li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
 </ol>
 </div>
 </section>
@@ -281,6 +281,8 @@ <h2 id="additional-topics-kernel-regression-gaussian-processes-and-bayesian-stat
 large number of variables and a particular outcome (dependent
 variable).
 </p>
+
+<p>These topics are not covered by the lectures but can be used to define projects.</p>
 </section>
 
 <section>
@@ -397,14 +399,18 @@ <h2 id="good-books-with-hands-on-material-and-codes">Good books with hands-on ma
 </section>
 
 <section>
-<h2 id="twst-yourself-deep-learning-1">Twst yourself: Deep learning 1  </h2>
+<h2 id="test-yourself-deep-learning-1">Test yourself: Deep learning 1  </h2>
+
+<p>Deep learning (essentially neural networks)
+background knowledge we deem important to be familiar with.
+</p>
 
 <ol>
-<p><li> Describe the architecture of a typical feed forward  Neural Network (NN).</li> 
+<p><li> Can you describe the architecture of a typical feed forward  Neural Network (NN).</li> 
 <p><li> What is an activation function and discuss the use of an activation function.</li>
 <p><li> Can you name and explain three different types of activation functions?</li>
 <p><li> You are using a deep neural network for a prediction task. After training your model, you notice that it is strongly overfitting the training set and that the performance on the test isn&#8217;t good. What can you do to reduce overfitting?</li>
-<p><li> How would you know if your model is suffering from the problem of exploding Gradients?</li>
+<p><li> How would you know if your model is suffering from the problem of exploding gradients?</li>
 <p><li> Can you name and explain a few hyperparameters used for training a neural network?</li>
 </ol>
 </section>

doc/pub/week1/html/week1-solarized.html

@@ -110,10 +110,10 @@
                2,
                None,
                'good-books-with-hands-on-material-and-codes'),
-              ('Twst yourself: Deep learning 1',
+              ('Test yourself: Deep learning 1',
                2,
                None,
-               'twst-yourself-deep-learning-1'),
+               'test-yourself-deep-learning-1'),
               ('Test yourself: Deep learning 2',
                2,
                None,
@@ -399,12 +399,12 @@ <h2 id="overview-of-first-week-january-19-23-2026">Overview of first week, Janua
 <b></b>
 <p>
 <ol>
- <li> Presentation of course</li>
- <li> Discussion of possible projects</li>
- <li> Deep learning methods, mathematics and  review of neural networks
+<li> Presentation of course</li>
+<li> Discussion of possible projects</li>
+<li> Deep learning methods, mathematics and  review of neural networks
 <!-- o "Video of lecture at <a href="https://youtu.be/SY57dC46L9o" target="_blank"><tt>https://youtu.be/SY57dC46L9o</tt></a> --></li>
- <li> Recommended reading first three weeks: Raschka et al chapter 11 and Goodfellow et al chapters 6 and 7</li>
- <li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
+<li> Recommended reading first three weeks: Raschka et al chapters 11-12 and Goodfellow et al chapters 6-8</li>
+<li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
 </ol>
 </div>
 
@@ -471,6 +471,8 @@ <h2 id="additional-topics-kernel-regression-gaussian-processes-and-bayesian-stat
 variable).
 </p>
 
+<p>These topics are not covered by the lectures but can be used to define projects.</p>
+
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
 <h2 id="project-paths-overarching-view">Project paths, overarching view </h2>
 
@@ -577,14 +579,18 @@ <h2 id="good-books-with-hands-on-material-and-codes">Good books with hands-on ma
 </p>
 
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
-<h2 id="twst-yourself-deep-learning-1">Twst yourself: Deep learning 1  </h2>
+<h2 id="test-yourself-deep-learning-1">Test yourself: Deep learning 1  </h2>
+
+<p>Deep learning (essentially neural networks)
+background knowledge we deem important to be familiar with.
+</p>
 
 <ol>
-<li> Describe the architecture of a typical feed forward  Neural Network (NN).</li> 
+<li> Can you describe the architecture of a typical feed forward  Neural Network (NN).</li> 
 <li> What is an activation function and discuss the use of an activation function.</li>
 <li> Can you name and explain three different types of activation functions?</li>
 <li> You are using a deep neural network for a prediction task. After training your model, you notice that it is strongly overfitting the training set and that the performance on the test isn&#8217;t good. What can you do to reduce overfitting?</li>
-<li> How would you know if your model is suffering from the problem of exploding Gradients?</li>
+<li> How would you know if your model is suffering from the problem of exploding gradients?</li>
 <li> Can you name and explain a few hyperparameters used for training a neural network?</li>
 </ol>
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -1838,7 +1844,7 @@ <h2 id="updating-the-gradients">Updating the gradients  </h2>
 
 <!-- ------------------- end of main content --------------- -->
 <center style="font-size:80%">
-<!-- copyright --> &copy; 1999-2025, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+<!-- copyright --> &copy; 1999-2026, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
 </center>
 </body>
 </html>

doc/pub/week1/html/week1.html

@@ -187,10 +187,10 @@
                2,
                None,
                'good-books-with-hands-on-material-and-codes'),
-              ('Twst yourself: Deep learning 1',
+              ('Test yourself: Deep learning 1',
                2,
                None,
-               'twst-yourself-deep-learning-1'),
+               'test-yourself-deep-learning-1'),
               ('Test yourself: Deep learning 2',
                2,
                None,
@@ -476,12 +476,12 @@ <h2 id="overview-of-first-week-january-19-23-2026">Overview of first week, Janua
 <b></b>
 <p>
 <ol>
- <li> Presentation of course</li>
- <li> Discussion of possible projects</li>
- <li> Deep learning methods, mathematics and  review of neural networks
+<li> Presentation of course</li>
+<li> Discussion of possible projects</li>
+<li> Deep learning methods, mathematics and  review of neural networks
 <!-- o "Video of lecture at <a href="https://youtu.be/SY57dC46L9o" target="_blank"><tt>https://youtu.be/SY57dC46L9o</tt></a> --></li>
- <li> Recommended reading first three weeks: Raschka et al chapter 11 and Goodfellow et al chapters 6 and 7</li>
- <li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
+<li> Recommended reading first three weeks: Raschka et al chapters 11-12 and Goodfellow et al chapters 6-8</li>
+<li> Permanent Zoom link for the whole semester is <a href="https://uio.zoom.us/my/mortenhj" target="_blank"><tt>https://uio.zoom.us/my/mortenhj</tt></a></li>
 </ol>
 </div>
 
@@ -548,6 +548,8 @@ <h2 id="additional-topics-kernel-regression-gaussian-processes-and-bayesian-stat
 variable).
 </p>
 
+<p>These topics are not covered by the lectures but can be used to define projects.</p>
+
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
 <h2 id="project-paths-overarching-view">Project paths, overarching view </h2>
 
@@ -654,14 +656,18 @@ <h2 id="good-books-with-hands-on-material-and-codes">Good books with hands-on ma
 </p>
 
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
-<h2 id="twst-yourself-deep-learning-1">Twst yourself: Deep learning 1  </h2>
+<h2 id="test-yourself-deep-learning-1">Test yourself: Deep learning 1  </h2>
+
+<p>Deep learning (essentially neural networks)
+background knowledge we deem important to be familiar with.
+</p>
 
 <ol>
-<li> Describe the architecture of a typical feed forward  Neural Network (NN).</li> 
+<li> Can you describe the architecture of a typical feed forward  Neural Network (NN).</li> 
 <li> What is an activation function and discuss the use of an activation function.</li>
 <li> Can you name and explain three different types of activation functions?</li>
 <li> You are using a deep neural network for a prediction task. After training your model, you notice that it is strongly overfitting the training set and that the performance on the test isn&#8217;t good. What can you do to reduce overfitting?</li>
-<li> How would you know if your model is suffering from the problem of exploding Gradients?</li>
+<li> How would you know if your model is suffering from the problem of exploding gradients?</li>
 <li> Can you name and explain a few hyperparameters used for training a neural network?</li>
 </ol>
 <!-- !split --><br><br><br><br><br><br><br><br><br><br>
@@ -1915,7 +1921,7 @@ <h2 id="updating-the-gradients">Updating the gradients  </h2>
 
 <!-- ------------------- end of main content --------------- -->
 <center style="font-size:80%">
-<!-- copyright --> &copy; 1999-2025, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
+<!-- copyright --> &copy; 1999-2026, Morten Hjorth-Jensen. Released under CC Attribution-NonCommercial 4.0 license
 </center>
 </body>
 </html>