PURELIN Linear transfer function.
Syntax
A = purelin(N,FP)
dA_dN = purelin('dn',N,A,FP)
INFO = purelin(CODE)
Description
PURELIN is a neural transfer function. Transfer functions
calculate a layer's output from its net input.
PURELIN(N,FP) takes N and optional function parameters,
N - SxQ matrix of net input (column) vectors.
FP - Struct of function parameters (ignored).
and returns A, an SxQ matrix equal to N.
PURELIN('dn',N,A,FP) returns SxQ derivative of A w-respect to N.
If A or FP are not supplied or are set to [], FP reverts to
the default parameters, and A is calculated from N.
PURELIN('name') returns the name of this function.
PURELIN('output',FP) returns the [min max] output range.
PURELIN('active',FP) returns the [min max] active input range.
PURELIN('fullderiv') returns 1 or 0, whether DA_DN is SxSxQ or SxQ.
PURELIN('fpnames') returns the names of the function parameters.
PURELIN('fpdefaults') returns the default function parameters.
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)
Here we assign this transfer function to layer i of a network.
net.layers{i}.transferFcn = 'purelin';
Algorithm
a = purelin(n) = n