19.3.5 Deep Neural Networks

Next, we train a deep feed-forward concurrent neural network (CNN) for binary classification. The network architecture is shown in Fig. 3. Fig. 3. Structure of CNN classifier The CNN consists of an input layer, 2 convolution layers, 2 pooling layers, 2 fully connected layers, and an output layer. Each pooling layer obtains the result of the former layer and cuts the output size into one h...