Neural Network Toolbox

satlins

Symmetric saturating linear transfer function

Graph and Symbol

Syntax

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

Description

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

satlins(N) takes one input,

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

and returns values of N truncated into the interval [-1, 1].

satlins(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 satlins transfer function.

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

Network Use

You can create a standard network that uses satlins by calling newhop.

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

In either case, call sim to simulate the network with satlins. See newhop for simulation examples.

Algorithm

satlins(n) = -1, if n <= -1; n, if -1 <= n <= 1; 1, if 1 <= n.

See Also

• sim, satlin, poslin, purelin
  

satlin

seq2con

© 1994-2005 The MathWorks, Inc.