Neural Network Toolbox

Summary

Perceptrons are useful as classifiers. They can classify linearly separable input vectors very well. Convergence is guaranteed in a finite number of steps providing the perceptron can solve the problem.

The design of a perceptron network is constrained completely by the problem to be solved. Perceptrons have a single layer of hard-limit neurons. The number of network inputs and the number of neurons in the layer are constrained by the number of inputs and outputs required by the problem.

Training time is sensitive to outliers, but outlier input vectors do not stop the network from finding a solution.

Single-layer perceptrons can solve problems only when data is linearly separable. This is seldom the case. One solution to this difficulty is to use a preprocessing method that results in linearly separable vectors. Or you might use multiple perceptrons in multiple layers. Alternatively, you can use other kinds of networks such as linear networks or backpropagation networks, which can classify nonlinearly separable input vectors.

A graphical user interface can be used to create networks and data, train the networks, and export the networks and data to the command line workspace.

Save a Variable to a File and Load It Later

Figures and Equations

© 1994-2005 The MathWorks, Inc.