Neural Network Toolbox

Design of General Linear Networks

The function newlind now allows the design of linear networks with multiple inputs, outputs, and input delays.

Improved Early Stopping

Early stopping can now be used in combination with Bayesian regularization. In some cases this can improve the generalization capability of the trained network.

Generalization and Speed Benchmarks

Generalization benchmarks comparing the performance of Bayesian regularization and early stopping are provided. We also include speed benchmarks, which compare the speed of convergence of the various training algorithms on a variety of problems in pattern recognition and function approximation. These benchmarks can aid users in selecting the appropriate algorithm for their problem.

Demonstration of a Sample Training Session

A new demonstration that illustrates a sample training session is included in Chapter 5. A sample training session script is also provided. Users can modify this script to fit their problem.

New Training Functions

Neural Network Applications

© 1994-2005 The MathWorks, Inc.