Neural Networks
Internal
Overview
A neural network consists of several layers of activation units ("individual neurons"), where one layer's activation unit output is connected to the inputs of all activation units of the successive layer. The behavior of an individual activation unit is described here. A neural network's topology, along with notations and conventions, are discussed here. A neural network produces predictions by forward propagating activations across its layers from left to right, until the output layer computes the hypothesis function, for a specific input sample. The forward propagation process is described here. Forward propagation is performed based on a set of parameters (or weights) that are obtained by training the network. Training the network, or "fitting the parameters", is performed by a backpropagation algorithm, which is described here.