update

Author: mhjensen

doc/pub/week47/html/._week47-bs018.html

@@ -412,6 +412,7 @@ <h2 id="pytorch-defining-a-simple-rnn-using-tensorflow" class="anchor">PyTorch:
 In this code we have used
 </p>
 <ol>
+<li> sequence$\_$length is the number of time steps in each input sequence fed into a recurrent neural network. It represents how many time points we provide at once. It is the number of ordered observations in each sample of our dataset.</li>
 <li> return_sequences=False makes it output only the last hidden state, which is fed to the classifier. Also, we have</li>
 <li> from_logits=True matches the PyTorch CrossEntropyLoss.</li>
 </ol>

doc/pub/week47/html/week47-reveal.html

@@ -518,6 +518,7 @@ <h2 id="pytorch-defining-a-simple-rnn-using-tensorflow">PyTorch: Defining a Simp
 In this code we have used
 </p>
 <ol>
+<p><li> sequence$\_$length is the number of time steps in each input sequence fed into a recurrent neural network. It represents how many time points we provide at once. It is the number of ordered observations in each sample of our dataset.</li>
 <p><li> return_sequences=False makes it output only the last hidden state, which is fed to the classifier. Also, we have</li>
 <p><li> from_logits=True matches the PyTorch CrossEntropyLoss.</li>
 </ol>

doc/pub/week47/html/week47-solarized.html

@@ -592,6 +592,7 @@ <h2 id="pytorch-defining-a-simple-rnn-using-tensorflow">PyTorch: Defining a Simp
 In this code we have used
 </p>
 <ol>
+<li> sequence$\_$length is the number of time steps in each input sequence fed into a recurrent neural network. It represents how many time points we provide at once. It is the number of ordered observations in each sample of our dataset.</li>
 <li> return_sequences=False makes it output only the last hidden state, which is fed to the classifier. Also, we have</li>
 <li> from_logits=True matches the PyTorch CrossEntropyLoss.</li>
 </ol>

doc/pub/week47/html/week47.html

@@ -669,6 +669,7 @@ <h2 id="pytorch-defining-a-simple-rnn-using-tensorflow">PyTorch: Defining a Simp
 In this code we have used
 </p>
 <ol>
+<li> sequence$\_$length is the number of time steps in each input sequence fed into a recurrent neural network. It represents how many time points we provide at once. It is the number of ordered observations in each sample of our dataset.</li>
 <li> return_sequences=False makes it output only the last hidden state, which is fed to the classifier. Also, we have</li>
 <li> from_logits=True matches the PyTorch CrossEntropyLoss.</li>
 </ol>