Neural networks – a primer

The RBM is a form of recurrent neural network. In order to understand how the RBM works, it is necessary to have a more general understanding of neural networks. Readers with an understanding of artificial neural network (hereafter neural network, for the sake of simplicity) algorithms will find familiar elements in the following description.

There are many accounts that cover neural networks in great theoretical detail; we won't go into great detail retreading this ground. For the purposes of this chapter, we will first describe the components of a neural network, common architectures, and prevalent learning processes.

The composition of a neural network

For unfamiliar readers, neural networks are a class of mathematical models that train to produce and optimize a definition for a function (or distribution) over a set of input features. The specific objective of a given neural network application can be defined by the operator using a performance measure...