Neural Network Toolbox

Custom Functions

The toolbox allows you to create and use many kinds of functions. This gives you a great deal of control over the algorithms used to initialize, simulate, and train; and allow adaption for your networks.

The following sections describe how to create your own versions of these kinds of functions:

• Simulation functions
• Transfer functions
• Net input functions
• Weight functions
• Initialization functions
• Network initialization functions
• Layer initialization functions
• Weight and bias initialization functions
• Learning functions
• Network training functions
• Network adapt functions
• Network performance functions
• Weight and bias learning functions
• Self-organizing map functions
• Topology functions
• Distance functions

Learning Functions

Simulation Functions

© 1994-2005 The MathWorks, Inc.