Introduction :: Perceptrons (Neural Network Toolbox)

Neural Network Toolbox

Introduction

This chapter has a number of objectives. First we want to introduce you to learning rules, methods of deriving the next changes that might be made in a network, and training, a procedure whereby a network is actually adjusted to do a particular job. Along the way we discuss a toolbox function to create a simple perceptron network, and we also cover functions to initialize and simulate such networks. We use the perceptron as a vehicle for tying these concepts together.

Rosenblatt [Rose61] created many variations of the perceptron. One of the simplest was a single-layer network whose weights and biases could be trained to produce a correct target vector when presented with the corresponding input vector. The training technique used is called the perceptron learning rule. The perceptron generated great interest due to its ability to generalize from its training vectors and learn from initially randomly distributed connections. Perceptrons are especially suited for simple problems in pattern classification. They are fast and reliable networks for the problems they can solve. In addition, an understanding of the operations of the perceptron provides a good basis for understanding more complex networks.

In this chapter we define what we mean by a learning rule, explain the perceptron network and its learning rule, and tell you how to initialize and simulate perceptron networks.

The discussion of perceptron in this chapter is necessarily brief. For a more thorough discussion, see Chapter 4 "Perceptron Learning Rule" of [HDB1996], which discusses the use of multiple layers of perceptrons to solve more difficult problems beyond the capability of one layer.

You also may want to refer to the original book on the perceptron, Rosenblatt, F., Principles of Neurodynamics, Washington D.C.: Spartan Press, 1961. [Rose61].

Important Perceptron Functions

Entering help percept at the MATLAB® command line displays all the functions that are related to perceptrons.

Perceptron networks can be created with the function newp. These networks can be initialized, simulated and trained with init, sim and train. The following material describes how perceptrons work and introduces these functions.

Perceptrons Neuron Model