update

Author: mhjensen

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

@@ -82,11 +82,14 @@
                2,
                None,
                'same-code-but-now-with-momentum-gradient-descent'),
-              ('Overview video on Stochastic Gradient Descent',
+              ('Overview video on Stochastic Gradient Descent (SGD)',
                2,
                None,
-               'overview-video-on-stochastic-gradient-descent'),
+               'overview-video-on-stochastic-gradient-descent-sgd'),
               ('Batches and mini-batches', 2, None, 'batches-and-mini-batches'),
+              ('Pros and cons', 2, None, 'pros-and-cons'),
+              ('Convergence rates', 2, None, 'convergence-rates'),
+              ('Accuracy', 2, None, 'accuracy'),
               ('Stochastic Gradient Descent (SGD)',
                2,
                None,
@@ -129,19 +132,30 @@
                2,
                None,
                'algorithms-and-codes-for-adagrad-rmsprop-and-adam'),
+              ('AdaGrad algorithm, taken from "Goodfellow et '
+               'al":"https://www.deeplearningbook.org/contents/optimization.html"',
+               2,
+               None,
+               'adagrad-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html'),
+              ('RMSProp algorithm, taken from "Goodfellow et '
+               'al":"https://www.deeplearningbook.org/contents/optimization.html"',
+               2,
+               None,
+               'rmsprop-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html'),
+              ('ADAM algorithm, taken from "Goodfellow et '
+               'al":"https://www.deeplearningbook.org/contents/optimization.html"',
+               2,
+               None,
+               'adam-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html'),
               ('Practical tips', 2, None, 'practical-tips'),
-              ('Sneaking in  automatic differentiation using Autograd',
+              ('Sneaking in auotmatic differentiation using Autograd',
                2,
                None,
-               'sneaking-in-automatic-differentiation-using-autograd'),
+               'sneaking-in-auotmatic-differentiation-using-autograd'),
               ('Same code but now with momentum gradient descent',
                2,
                None,
                'same-code-but-now-with-momentum-gradient-descent'),
-              ("But none of these can compete with Newton's method",
-               2,
-               None,
-               'but-none-of-these-can-compete-with-newton-s-method'),
               ('Including Stochastic Gradient Descent with Autograd',
                2,
                None,
@@ -216,37 +230,42 @@
      <!-- navigation toc: --> <li><a href="._week37-bs012.html#program-example-for-gradient-descent-with-ridge-regression" style="font-size: 80%;">Program example for gradient descent with Ridge Regression</a></li>
      <!-- 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#improving-gradient-descent-with-momentum" style="font-size: 80%;">Improving gradient descent with momentum</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs041.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-bs016.html#overview-video-on-stochastic-gradient-descent" style="font-size: 80%;">Overview video on Stochastic Gradient Descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs043.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-bs016.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-bs017.html#batches-and-mini-batches" style="font-size: 80%;">Batches and mini-batches</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs018.html#stochastic-gradient-descent-sgd" style="font-size: 80%;">Stochastic Gradient Descent (SGD)</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs019.html#stochastic-gradient-descent" style="font-size: 80%;">Stochastic Gradient Descent</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs020.html#computation-of-gradients" style="font-size: 80%;">Computation of gradients</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs021.html#sgd-example" style="font-size: 80%;">SGD example</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs022.html#the-gradient-step" style="font-size: 80%;">The gradient step</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs023.html#simple-example-code" style="font-size: 80%;">Simple example code</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs024.html#when-do-we-stop" style="font-size: 80%;">When do we stop?</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs025.html#slightly-different-approach" style="font-size: 80%;">Slightly different approach</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs026.html#time-decay-rate" style="font-size: 80%;">Time decay rate</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs027.html#code-with-a-number-of-minibatches-which-varies" style="font-size: 80%;">Code with a Number of Minibatches which varies</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs028.html#replace-or-not" style="font-size: 80%;">Replace or not</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs029.html#momentum-based-gd" style="font-size: 80%;">Momentum based GD</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs030.html#more-on-momentum-based-approaches" style="font-size: 80%;">More on momentum based approaches</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs031.html#momentum-parameter" style="font-size: 80%;">Momentum parameter</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs032.html#second-moment-of-the-gradient" style="font-size: 80%;">Second moment of the gradient</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs033.html#rms-prop" style="font-size: 80%;">RMS prop</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs034.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-bs035.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-bs036.html#practical-tips" style="font-size: 80%;">Practical tips</a></li>
-     <!-- navigation toc: --> <li><a href="._week37-bs037.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-bs041.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-bs039.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-bs040.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-bs041.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-bs042.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-bs043.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-bs044.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-bs045.html#material-for-the-lab-sessions" style="font-size: 80%;">Material for the lab sessions</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs018.html#pros-and-cons" style="font-size: 80%;">Pros and cons</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs019.html#convergence-rates" style="font-size: 80%;">Convergence rates</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs020.html#accuracy" style="font-size: 80%;">Accuracy</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs021.html#stochastic-gradient-descent-sgd" style="font-size: 80%;">Stochastic Gradient Descent (SGD)</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs022.html#stochastic-gradient-descent" style="font-size: 80%;">Stochastic Gradient Descent</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs023.html#computation-of-gradients" style="font-size: 80%;">Computation of gradients</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs024.html#sgd-example" style="font-size: 80%;">SGD example</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs025.html#the-gradient-step" style="font-size: 80%;">The gradient step</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs026.html#simple-example-code" style="font-size: 80%;">Simple example code</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs027.html#when-do-we-stop" style="font-size: 80%;">When do we stop?</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs028.html#slightly-different-approach" style="font-size: 80%;">Slightly different approach</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs029.html#time-decay-rate" style="font-size: 80%;">Time decay rate</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs030.html#code-with-a-number-of-minibatches-which-varies" style="font-size: 80%;">Code with a Number of Minibatches which varies</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs031.html#replace-or-not" style="font-size: 80%;">Replace or not</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs032.html#momentum-based-gd" style="font-size: 80%;">Momentum based GD</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs033.html#more-on-momentum-based-approaches" style="font-size: 80%;">More on momentum based approaches</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs034.html#momentum-parameter" style="font-size: 80%;">Momentum parameter</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs035.html#second-moment-of-the-gradient" style="font-size: 80%;">Second moment of the gradient</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs036.html#rms-prop" style="font-size: 80%;">RMS prop</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs037.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-bs038.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-bs038.html#adagrad-algorithm-taken-from-goodfellow-et-al-https-www-deeplearningbook-org-contents-optimization-html" style="font-size: 80%;">AdaGrad algorithm, taken from "Goodfellow et al":"https://www.deeplearningbook.org/contents/optimization.html"</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs038.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-bs038.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-bs039.html#practical-tips" style="font-size: 80%;">Practical tips</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs040.html#sneaking-in-auotmatic-differentiation-using-autograd" style="font-size: 80%;">Sneaking in auotmatic differentiation using Autograd</a></li>
+     <!-- navigation toc: --> <li><a href="._week37-bs043.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-bs042.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-bs043.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-bs044.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-bs045.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-bs046.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-bs047.html#material-for-the-lab-sessions" style="font-size: 80%;">Material for the lab sessions</a></li>
 
         </ul>
       </li>
@@ -300,7 +319,7 @@ <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-bs045.html">46</a></li>
+  <li><a href="._week37-bs047.html">48</a></li>
   <li><a href="._week37-bs001.html">&raquo;</a></li>
 </ul>
 <!-- ------------------- end of main content --------------- -->