radbasn

(To be removed) Normalized radial basis transfer function

radbasn will be removed in a future release. For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.

For advice on updating your code, see Version History.

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	S-by-Q matrix of net input (column) vectors
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

R2026a: radbasn will be removed

radbasn will be removed in a future release.

To learn more about using activation and transfer functions in neural networks, see these examples and topics:

• Build Networks with Deep Network Designer

• List of Deep Learning Layers

• List of Functions with dlarray Support

• Compare Activation Layers

• Example Deep Learning Network Architectures

For more information, see Transition Legacy Neural Network Code to dlnetwork Workflows.