updating

Author: mhjensen

doc/pub/week37/html/._week37-bs000.html

@@ -154,6 +154,27 @@
                2,
                None,
                'adam-optimizer-https-arxiv-org-abs-1412-6980'),
+              ('Why Combine Momentum and RMSProp?',
+               2,
+               None,
+               'why-combine-momentum-and-rmsprop'),
+              ('Adam: Exponential Moving Averages (Moments)',
+               2,
+               None,
+               'adam-exponential-moving-averages-moments'),
+              ('Adam: Bias Correction', 2, None, 'adam-bias-correction'),
+              ('Adam: Update Rule Derivation',
+               2,
+               None,
+               'adam-update-rule-derivation'),
+              ('Adam vs. AdaGrad and RMSProp',
+               2,
+               None,
+               'adam-vs-adagrad-and-rmsprop'),
+              ('Adaptivity Across Dimensions',
+               2,
+               None,
+               'adaptivity-across-dimensions'),
               ('ADAM algorithm, taken from "Goodfellow et '
                'al":"https://www.deeplearningbook.org/contents/optimization.html"',
                2,
@@ -264,7 +285,7 @@
      <!-- navigation toc: --> <li><a href="._week37-bs013.html#using-gradient-descent-methods-limitations" style="font-size: 80%;">Using gradient descent methods, limitations</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs014.html#momentum-based-gd" style="font-size: 80%;">Momentum based GD</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs015.html#improving-gradient-descent-with-momentum" style="font-size: 80%;">Improving gradient descent with momentum</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs047.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs053.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs017.html#overview-video-on-stochastic-gradient-descent-sgd" style="font-size: 80%;">Overview video on Stochastic Gradient Descent (SGD)</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs018.html#batches-and-mini-batches" style="font-size: 80%;">Batches and mini-batches</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs019.html#pros-and-cons" style="font-size: 80%;">Pros and cons</a></li>
@@ -292,22 +313,28 @@
      <!-- navigation toc: --> <li><a href="._week37-bs039.html#rmsprop-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html" style="font-size: 80%;">RMSProp algorithm, taken from "Goodfellow et al":"https://www.deeplearningbook.org/contents/optimization.html"</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs040.html#adam-optimizer" style="font-size: 80%;">Adam Optimizer</a></li>
      <!-- navigation toc: --> <li><a href="._week37-bs041.html#adam-optimizer-https-arxiv-org-abs-1412-6980" style="font-size: 80%;">"ADAM optimizer":"https://arxiv.org/abs/1412.6980"</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs041.html#adam-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html" style="font-size: 80%;">ADAM algorithm, taken from "Goodfellow et al":"https://www.deeplearningbook.org/contents/optimization.html"</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs042.html#algorithms-and-codes-for-adagrad-rmsprop-and-adam" style="font-size: 80%;">Algorithms and codes for Adagrad, RMSprop and Adam</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs043.html#practical-tips" style="font-size: 80%;">Practical tips</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs044.html#sneaking-in-automatic-differentiation-using-autograd" style="font-size: 80%;">Sneaking in automatic differentiation using Autograd</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs047.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs046.html#including-stochastic-gradient-descent-with-autograd" style="font-size: 80%;">Including Stochastic Gradient Descent with Autograd</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs047.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs048.html#but-none-of-these-can-compete-with-newton-s-method" style="font-size: 80%;">But none of these can compete with Newton's method</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs049.html#similar-second-order-function-now-problem-but-now-with-adagrad" style="font-size: 80%;">Similar (second order function now) problem but now with AdaGrad</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs050.html#rmsprop-for-adaptive-learning-rate-with-stochastic-gradient-descent" style="font-size: 80%;">RMSprop for adaptive learning rate with Stochastic Gradient Descent</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs051.html#and-finally-adam-https-arxiv-org-pdf-1412-6980-pdf" style="font-size: 80%;">And finally "ADAM":"https://arxiv.org/pdf/1412.6980.pdf"</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs052.html#material-for-the-lab-sessions" style="font-size: 80%;">Material for the lab sessions</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs053.html#reminder-on-different-scaling-methods" style="font-size: 80%;">Reminder on different scaling methods</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs054.html#functionality-in-scikit-learn" style="font-size: 80%;">Functionality in Scikit-Learn</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs055.html#more-preprocessing" style="font-size: 80%;">More preprocessing</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs056.html#frequently-used-scaling-functions" style="font-size: 80%;">Frequently used scaling functions</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs042.html#why-combine-momentum-and-rmsprop" style="font-size: 80%;">Why Combine Momentum and RMSProp?</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs043.html#adam-exponential-moving-averages-moments" style="font-size: 80%;">Adam: Exponential Moving Averages (Moments)</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs044.html#adam-bias-correction" style="font-size: 80%;">Adam: Bias Correction</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs045.html#adam-update-rule-derivation" style="font-size: 80%;">Adam: Update Rule Derivation</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs046.html#adam-vs-adagrad-and-rmsprop" style="font-size: 80%;">Adam vs. AdaGrad and RMSProp</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs047.html#adaptivity-across-dimensions" style="font-size: 80%;">Adaptivity Across Dimensions</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs047.html#adam-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html" style="font-size: 80%;">ADAM algorithm, taken from "Goodfellow et al":"https://www.deeplearningbook.org/contents/optimization.html"</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs048.html#algorithms-and-codes-for-adagrad-rmsprop-and-adam" style="font-size: 80%;">Algorithms and codes for Adagrad, RMSprop and Adam</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs049.html#practical-tips" style="font-size: 80%;">Practical tips</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs050.html#sneaking-in-automatic-differentiation-using-autograd" style="font-size: 80%;">Sneaking in automatic differentiation using Autograd</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs053.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs052.html#including-stochastic-gradient-descent-with-autograd" style="font-size: 80%;">Including Stochastic Gradient Descent with Autograd</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs053.html#same-code-but-now-with-momentum-gradient-descent" style="font-size: 80%;">Same code but now with momentum gradient descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs054.html#but-none-of-these-can-compete-with-newton-s-method" style="font-size: 80%;">But none of these can compete with Newton's method</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs055.html#similar-second-order-function-now-problem-but-now-with-adagrad" style="font-size: 80%;">Similar (second order function now) problem but now with AdaGrad</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs056.html#rmsprop-for-adaptive-learning-rate-with-stochastic-gradient-descent" style="font-size: 80%;">RMSprop for adaptive learning rate with Stochastic Gradient Descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs057.html#and-finally-adam-https-arxiv-org-pdf-1412-6980-pdf" style="font-size: 80%;">And finally "ADAM":"https://arxiv.org/pdf/1412.6980.pdf"</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs058.html#material-for-the-lab-sessions" style="font-size: 80%;">Material for the lab sessions</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs059.html#reminder-on-different-scaling-methods" style="font-size: 80%;">Reminder on different scaling methods</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs060.html#functionality-in-scikit-learn" style="font-size: 80%;">Functionality in Scikit-Learn</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs061.html#more-preprocessing" style="font-size: 80%;">More preprocessing</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs062.html#frequently-used-scaling-functions" style="font-size: 80%;">Frequently used scaling functions</a></li>
 
         </ul>
       </li>
@@ -361,7 +388,7 @@ <h4>September 8-12, 2025</h4>
   <li><a href="._week37-bs008.html">9</a></li>
   <li><a href="._week37-bs009.html">10</a></li>
   <li><a href="">...</a></li>
-  <li><a href="._week37-bs056.html">57</a></li>
+  <li><a href="._week37-bs062.html">63</a></li>
   <li><a href="._week37-bs001.html">&raquo;</a></li>
 </ul>
 <!-- ------------------- end of main content --------------- -->