purelin

Linear transfer function

Syntax

A = purelin(N)

info = purelin('code')

A = purelin(N) takes an S-by-Q matrix of net input (column) vectors, N, and returns an S-by-Q matrix equal to N, A.

A plot of the linear transfer function. The output scales linearly with the input.

info = purelin('code') returns useful information for each code character vector:

purelin('name') returns the name of this function.
purelin('output') returns the [min max] output range.
purelin('active') returns the [min max] active input range.
purelin('fullderiv') returns 1 or 0, depending on whether dA_dN is S-by-S-by-Q or S-by-Q.
purelin('fpnames') returns the names of the function parameters.
purelin('fpdefaults') returns the default function parameters.

This example shows how to create and plot a purelin transfer function and assign it to layer i in a network.

Create a plot of the purelin transfer function:

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

Assign this transfer function to layer i in a network.

net.layers{i}.transferFcn = 'purelin';

Net column vector inputs, specified as anS-by-Q matrix.

Linear transfer function, returned as an S-by-Q matrix.

a = purelin(n) = n

Introduced before R2006a