Neural Network Toolbox

purelin

Linear transfer function

Graph and Symbol

Syntax

• A = purelin(N)
  info = purelin(code)
  

Description

purelin is a transfer function. Transfer functions calculate a layer's output from its net input.

purelin(N) takes one input,

• N -- S x Q matrix of net input (column) vectors

and returns N.

purelin(code) returns useful information for each code string:

• 'deriv' -- Name of derivative function

  'name' -- Full name

  'output' -- Output range

  'active' -- Active input range

Examples

Here is the code to create a plot of the purelin transfer function.

• n = -5:0.1:5;
  a = purelin(n);
  plot(n,a)
  

Network Use

You can create a standard network that uses purelin by calling newlin or newlind.

To change a network so a layer uses purelin, set net.layers{i}.transferFcn to 'purelin'.

In either case, call sim to simulate the network with purelin. See newlin or newlind for simulation examples.

Algorithm

• purelin(n) = n
  

See Also

• sim, dpurelin, satlin, satlins
  

prestd

quant

© 1994-2005 The MathWorks, Inc.