CNNs are conceptually similar to the feedforward neural networks we covered in the previous chapter. They consist of units that contain parameters, called weights and biases, and the training process adjusts these parameters to optimize the network's output for a given input. Each unit applies its parameters to a linear operation on the input data or activations received from other units, possibly followed by a non-linear transformation.
The overall network models a differentiable function that maps raw data, for example, image pixels to class probabilities, using an output activation such as the softmax function. CNNs also use a loss function such as cross-entropy to compute a single quality metric from the output layer, and use the gradients of the loss with respect to the network parameter to learn.
Feedforward neural networks with fully-connected layers...
