Convolutional nets are multiple-layer feedforward networks (MLFNs) having a special structure that makes them especially useful in computer vision. In this chapter, we will review MLFNs and then show how their structure can be specialized for image processing.
Review of Multiple-Layer Feedforward Networks
A multiple-layer feedforward network is generally illustrated as a stack of layers of “neurons” similar to what is shown in Figure 1-1 and Figure 1-2. The bottom layer is the input to the network, what would be referred to as the independent variables or
