Slides reordering

2.1-Introduction_to_ANN.html

@@ -3768,7 +3768,8 @@ <h3 class="anchored" data-anchor-id="a-more-compact-notation">A more compact not
 <section id="multiple-architectures-for-ann" class="level2">
 <h2 class="anchored" data-anchor-id="multiple-architectures-for-ann">Multiple architectures for ANN</h2>
 <ul>
-<li><p>We have so far focused on a single hidden layer neural network of the example One can build neural networks with many distinct architectures (meaning patterns of connectivity between neurons), including ones with multiple hidden layers.</p></li>
+<li><p>We have so far focused on a single hidden layer neural network of the example.</p></li>
+<li><p>Indeed, One can build neural networks with many distinct architectures (meaning patterns of connectivity between neurons), including ones with multiple hidden layers.</p></li>
 <li><p>See <a href="https://www.asimovinstitute.org/neural-network-zoo/">here the Neural Network Zoo</a>.</p></li>
 </ul>
 <section id="feed-forward-neural-networks" class="level3">

2.1-Introduction_to_ANN.qmd

@@ -689,7 +689,9 @@ $$
 ## Multiple architectures for ANN
 
 -   We have so far focused on a single hidden layer neural network of
-    the example One can build neural networks with many distinct
+    the example.
+
+- Indeed, One can build neural networks with many distinct
     architectures (meaning patterns of connectivity between neurons),
     including ones with multiple hidden layers.
 
@@ -936,8 +938,7 @@ $N(0,0.01)$.
 
 # An example
 
-In this example we train and use a "shallow neural network", called this
-way in contrast with "deep neural networks".
+In this example we train and use a "shallow neural network", called this way in contrast with "deep neural networks".
 
 We will use the `neuralnet` R package, which is not intended to work
 with deep neural networks, to build a simple neural network to predict