satlin (Neural Network Toolbox)

Saturating linear transfer function

A = satlin(N)
info = satlin(code)

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

satlin(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].

satlin(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 satlin transfer function.

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

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

Call sim to simulate the network with satlin. See newhop for simulation examples.

satlin(n) = 0, if n <= 0; n, if 0 <= n <= 1; 1, if 1 <= n.