correcting typos

Author: mhjensen

doc/pub/week8/html/week8-bs.html

@@ -976,7 +976,7 @@ <h2 id="typical-aes" class="anchor">Typical AEs </h2>
 
 <p>The standard setup is done via a standard feed forward neural network (FFNN), or what is called a Feed Forward Autoencoder.</p>
 
-<p>A typical FFNN architecture has an odd number of layers and is symmetrical with respect to the middle layer.</p>
+<p>A typical FFNN architecture has a given  number of layers and is symmetrical with respect to the middle layer.</p>
 
 <p>Typically, the first layer has a number of neurons \( n_{1} = n \) which equals the size of the input observation \( \mathbf{x}_{\mathbf{i}} \).</p>
 

doc/pub/week8/html/week8-reveal.html

@@ -917,7 +917,7 @@ <h2 id="typical-aes">Typical AEs </h2>
 
 <p>The standard setup is done via a standard feed forward neural network (FFNN), or what is called a Feed Forward Autoencoder.</p>
 
-<p>A typical FFNN architecture has an odd number of layers and is symmetrical with respect to the middle layer.</p>
+<p>A typical FFNN architecture has a given  number of layers and is symmetrical with respect to the middle layer.</p>
 
 <p>Typically, the first layer has a number of neurons \( n_{1} = n \) which equals the size of the input observation \( \mathbf{x}_{\mathbf{i}} \).</p>
 

doc/pub/week8/html/week8-solarized.html

@@ -908,7 +908,7 @@ <h2 id="typical-aes">Typical AEs </h2>
 
 <p>The standard setup is done via a standard feed forward neural network (FFNN), or what is called a Feed Forward Autoencoder.</p>
 
-<p>A typical FFNN architecture has an odd number of layers and is symmetrical with respect to the middle layer.</p>
+<p>A typical FFNN architecture has a given  number of layers and is symmetrical with respect to the middle layer.</p>
 
 <p>Typically, the first layer has a number of neurons \( n_{1} = n \) which equals the size of the input observation \( \mathbf{x}_{\mathbf{i}} \).</p>
 

doc/pub/week8/html/week8.html

@@ -985,7 +985,7 @@ <h2 id="typical-aes">Typical AEs </h2>
 
 <p>The standard setup is done via a standard feed forward neural network (FFNN), or what is called a Feed Forward Autoencoder.</p>
 
-<p>A typical FFNN architecture has an odd number of layers and is symmetrical with respect to the middle layer.</p>
+<p>A typical FFNN architecture has a given  number of layers and is symmetrical with respect to the middle layer.</p>
 
 <p>Typically, the first layer has a number of neurons \( n_{1} = n \) which equals the size of the input observation \( \mathbf{x}_{\mathbf{i}} \).</p>