update week 5

Author: mhjensen

doc/pub/week5/html/week5-bs.html

@@ -806,11 +806,11 @@ <h2 id="example-of-how-we-can-up-a-model-without-a-specific-image" class="anchor
 
 <p>The 6 lines of code below define the convolutional base using a common pattern: a stack of Conv2D and MaxPooling2D layers.</p>
 
-<p>As input, a CNN takes tensors of shape (image_height, image_width,
-color_channels), ignoring the batch size. If you are new to these
-dimensions, color_channels refers to (R,G,B). In this example, you
+<p>As input, a CNN takes tensors of shape (image$\_$height, image$\_$width,
+color$\_$channels), ignoring the batch size. If you are new to these
+dimensions, color$\_$channels refers to (R,G,B). In this example, you
 will configure the CNN to process inputs of shape (32, 32, 3) as an
-example. You can do this by passing the argument input_shape to our
+example. You can do this by passing the argument input$\_$shape to our
 first layer.
 </p>
 
@@ -1344,10 +1344,10 @@ <h3 id="schedulers" class="anchor">Schedulers </h3>
 <p>The code below shows object oriented implementations of the Constant,
 Momentum, Adagrad, AdagradMomentum, RMS prop and Adam schedulers. All
 of the classes belong to the shared abstract Scheduler class, and
-share the update_change() and reset() methods allowing for any of the
+share the update$\_$change() and reset() methods allowing for any of the
 schedulers to be seamlessly used during the training stage, as will
 later be shown in the fit() method of the neural
-network. Update_change() only has one parameter, the gradient
+network. The function Update$\_$change() only has one parameter, the gradient
 (\( \delta^{l}_{j}a^{l-1}_k \)), and returns the change which will be
 subtracted from the weights. The reset() function takes no parameters,
 and resets the desired variables. For Constant and Momentum, reset
@@ -4098,8 +4098,8 @@ <h3 id="usage-of-cnn-code" class="anchor">Usage of CNN code </h3>
 </div>
 
 <p>Now that we have our CNN object, we can begin to add layers to it!
-Many of the add_layer functions have default values, for example
-add_Convolution2DLayer() has a default v_stride and h_stride of
+Many of the add$\_$layer functions have default values, for example
+add$\_$Convolution2DLayer() has a default v$\_$stride and h$\_$stride of
 1. However, these can of course be set to any value you please. Note
 that the input channels of a subsequent convolutional layer must equal
 the previous convolutional layer's feature maps.
@@ -4257,11 +4257,11 @@ <h3 id="usage-of-cnn-code" class="anchor">Usage of CNN code </h3>
 <p>The codebase allows for great flexibility in CNN
 architectures. Pooling layers can be added before, inbetween or after
 convolutional layers, but due to the great optimizations made within
-Convolution2DLayerOPT, we recommend using the v_stride and h_stride
-parameters in add_Convolution2DLayer() to reduce the dimentionality of
+Convolution2DLayerOPT, we recommend using the v$\_$stride and h$\_$stride
+parameters in add$\_$Convolution2DLayer() to reduce the dimentionality of
 the problem as the pooling layer is slow in comparison. To use the
 unoptimized version of Convolution2DLayer, simply pass optimized=False
-as an argument in add_Convolution2DLayer().
+as an argument in add$\_$Convolution2DLayer().
 </p>
 
 <p>If one wishes to perform binary classification using the CNN, simply

doc/pub/week5/html/week5-reveal.html

@@ -592,11 +592,11 @@ <h2 id="example-of-how-we-can-up-a-model-without-a-specific-image">Example of ho
 
 <p>The 6 lines of code below define the convolutional base using a common pattern: a stack of Conv2D and MaxPooling2D layers.</p>
 
-<p>As input, a CNN takes tensors of shape (image_height, image_width,
-color_channels), ignoring the batch size. If you are new to these
-dimensions, color_channels refers to (R,G,B). In this example, you
+<p>As input, a CNN takes tensors of shape (image$\_$height, image$\_$width,
+color$\_$channels), ignoring the batch size. If you are new to these
+dimensions, color$\_$channels refers to (R,G,B). In this example, you
 will configure the CNN to process inputs of shape (32, 32, 3) as an
-example. You can do this by passing the argument input_shape to our
+example. You can do this by passing the argument input$\_$shape to our
 first layer.
 </p>
 
@@ -1134,10 +1134,10 @@ <h3 id="schedulers">Schedulers </h3>
 <p>The code below shows object oriented implementations of the Constant,
 Momentum, Adagrad, AdagradMomentum, RMS prop and Adam schedulers. All
 of the classes belong to the shared abstract Scheduler class, and
-share the update_change() and reset() methods allowing for any of the
+share the update$\_$change() and reset() methods allowing for any of the
 schedulers to be seamlessly used during the training stage, as will
 later be shown in the fit() method of the neural
-network. Update_change() only has one parameter, the gradient
+network. The function Update$\_$change() only has one parameter, the gradient
 (\( \delta^{l}_{j}a^{l-1}_k \)), and returns the change which will be
 subtracted from the weights. The reset() function takes no parameters,
 and resets the desired variables. For Constant and Momentum, reset
@@ -3908,8 +3908,8 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 </div>
 
 <p>Now that we have our CNN object, we can begin to add layers to it!
-Many of the add_layer functions have default values, for example
-add_Convolution2DLayer() has a default v_stride and h_stride of
+Many of the add$\_$layer functions have default values, for example
+add$\_$Convolution2DLayer() has a default v$\_$stride and h$\_$stride of
 1. However, these can of course be set to any value you please. Note
 that the input channels of a subsequent convolutional layer must equal
 the previous convolutional layer's feature maps.
@@ -4068,11 +4068,11 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 <p>The codebase allows for great flexibility in CNN
 architectures. Pooling layers can be added before, inbetween or after
 convolutional layers, but due to the great optimizations made within
-Convolution2DLayerOPT, we recommend using the v_stride and h_stride
-parameters in add_Convolution2DLayer() to reduce the dimentionality of
+Convolution2DLayerOPT, we recommend using the v$\_$stride and h$\_$stride
+parameters in add$\_$Convolution2DLayer() to reduce the dimentionality of
 the problem as the pooling layer is slow in comparison. To use the
 unoptimized version of Convolution2DLayer, simply pass optimized=False
-as an argument in add_Convolution2DLayer().
+as an argument in add$\_$Convolution2DLayer().
 </p>
 
 <p>If one wishes to perform binary classification using the CNN, simply

doc/pub/week5/html/week5-solarized.html

@@ -714,11 +714,11 @@ <h2 id="example-of-how-we-can-up-a-model-without-a-specific-image">Example of ho
 
 <p>The 6 lines of code below define the convolutional base using a common pattern: a stack of Conv2D and MaxPooling2D layers.</p>
 
-<p>As input, a CNN takes tensors of shape (image_height, image_width,
-color_channels), ignoring the batch size. If you are new to these
-dimensions, color_channels refers to (R,G,B). In this example, you
+<p>As input, a CNN takes tensors of shape (image$\_$height, image$\_$width,
+color$\_$channels), ignoring the batch size. If you are new to these
+dimensions, color$\_$channels refers to (R,G,B). In this example, you
 will configure the CNN to process inputs of shape (32, 32, 3) as an
-example. You can do this by passing the argument input_shape to our
+example. You can do this by passing the argument input$\_$shape to our
 first layer.
 </p>
 
@@ -1252,10 +1252,10 @@ <h3 id="schedulers">Schedulers </h3>
 <p>The code below shows object oriented implementations of the Constant,
 Momentum, Adagrad, AdagradMomentum, RMS prop and Adam schedulers. All
 of the classes belong to the shared abstract Scheduler class, and
-share the update_change() and reset() methods allowing for any of the
+share the update$\_$change() and reset() methods allowing for any of the
 schedulers to be seamlessly used during the training stage, as will
 later be shown in the fit() method of the neural
-network. Update_change() only has one parameter, the gradient
+network. The function Update$\_$change() only has one parameter, the gradient
 (\( \delta^{l}_{j}a^{l-1}_k \)), and returns the change which will be
 subtracted from the weights. The reset() function takes no parameters,
 and resets the desired variables. For Constant and Momentum, reset
@@ -4006,8 +4006,8 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 </div>
 
 <p>Now that we have our CNN object, we can begin to add layers to it!
-Many of the add_layer functions have default values, for example
-add_Convolution2DLayer() has a default v_stride and h_stride of
+Many of the add$\_$layer functions have default values, for example
+add$\_$Convolution2DLayer() has a default v$\_$stride and h$\_$stride of
 1. However, these can of course be set to any value you please. Note
 that the input channels of a subsequent convolutional layer must equal
 the previous convolutional layer's feature maps.
@@ -4165,11 +4165,11 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 <p>The codebase allows for great flexibility in CNN
 architectures. Pooling layers can be added before, inbetween or after
 convolutional layers, but due to the great optimizations made within
-Convolution2DLayerOPT, we recommend using the v_stride and h_stride
-parameters in add_Convolution2DLayer() to reduce the dimentionality of
+Convolution2DLayerOPT, we recommend using the v$\_$stride and h$\_$stride
+parameters in add$\_$Convolution2DLayer() to reduce the dimentionality of
 the problem as the pooling layer is slow in comparison. To use the
 unoptimized version of Convolution2DLayer, simply pass optimized=False
-as an argument in add_Convolution2DLayer().
+as an argument in add$\_$Convolution2DLayer().
 </p>
 
 <p>If one wishes to perform binary classification using the CNN, simply

doc/pub/week5/html/week5.html

@@ -791,11 +791,11 @@ <h2 id="example-of-how-we-can-up-a-model-without-a-specific-image">Example of ho
 
 <p>The 6 lines of code below define the convolutional base using a common pattern: a stack of Conv2D and MaxPooling2D layers.</p>
 
-<p>As input, a CNN takes tensors of shape (image_height, image_width,
-color_channels), ignoring the batch size. If you are new to these
-dimensions, color_channels refers to (R,G,B). In this example, you
+<p>As input, a CNN takes tensors of shape (image$\_$height, image$\_$width,
+color$\_$channels), ignoring the batch size. If you are new to these
+dimensions, color$\_$channels refers to (R,G,B). In this example, you
 will configure the CNN to process inputs of shape (32, 32, 3) as an
-example. You can do this by passing the argument input_shape to our
+example. You can do this by passing the argument input$\_$shape to our
 first layer.
 </p>
 
@@ -1329,10 +1329,10 @@ <h3 id="schedulers">Schedulers </h3>
 <p>The code below shows object oriented implementations of the Constant,
 Momentum, Adagrad, AdagradMomentum, RMS prop and Adam schedulers. All
 of the classes belong to the shared abstract Scheduler class, and
-share the update_change() and reset() methods allowing for any of the
+share the update$\_$change() and reset() methods allowing for any of the
 schedulers to be seamlessly used during the training stage, as will
 later be shown in the fit() method of the neural
-network. Update_change() only has one parameter, the gradient
+network. The function Update$\_$change() only has one parameter, the gradient
 (\( \delta^{l}_{j}a^{l-1}_k \)), and returns the change which will be
 subtracted from the weights. The reset() function takes no parameters,
 and resets the desired variables. For Constant and Momentum, reset
@@ -4083,8 +4083,8 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 </div>
 
 <p>Now that we have our CNN object, we can begin to add layers to it!
-Many of the add_layer functions have default values, for example
-add_Convolution2DLayer() has a default v_stride and h_stride of
+Many of the add$\_$layer functions have default values, for example
+add$\_$Convolution2DLayer() has a default v$\_$stride and h$\_$stride of
 1. However, these can of course be set to any value you please. Note
 that the input channels of a subsequent convolutional layer must equal
 the previous convolutional layer's feature maps.
@@ -4242,11 +4242,11 @@ <h3 id="usage-of-cnn-code">Usage of CNN code </h3>
 <p>The codebase allows for great flexibility in CNN
 architectures. Pooling layers can be added before, inbetween or after
 convolutional layers, but due to the great optimizations made within
-Convolution2DLayerOPT, we recommend using the v_stride and h_stride
-parameters in add_Convolution2DLayer() to reduce the dimentionality of
+Convolution2DLayerOPT, we recommend using the v$\_$stride and h$\_$stride
+parameters in add$\_$Convolution2DLayer() to reduce the dimentionality of
 the problem as the pooling layer is slow in comparison. To use the
 unoptimized version of Convolution2DLayer, simply pass optimized=False
-as an argument in add_Convolution2DLayer().
+as an argument in add$\_$Convolution2DLayer().
 </p>
 
 <p>If one wishes to perform binary classification using the CNN, simply