radbasn
Normalized radial basis transfer function
Graph and Symbol
Syntax
A = radbasn(N,FP)
Description
radbasn
is a neural transfer function. Transfer functions calculate a
layer’s output from its net input. This function is equivalent to radbas, except that output
vectors are normalized by dividing by the sum of the pre-normalized values.
A = radbasn(N,FP)
takes one or two inputs,
N |
|
FP | Struct of function parameters (ignored) |
and returns A
, an S
-by-Q
matrix of
the radial basis function applied to each element of N
.
Examples
Here six random 3-element vectors are passed through the radial basis transform and normalized.
n = rand(3,6) a = radbasn(n)
Assign this transfer function to layer i
of a network.
net.layers{i}.transferFcn = 'radbasn';
Algorithms
a = radbasn(n) = exp(-n^2) / sum(exp(-n^2))
Version History
Introduced in R2010b