netinv

(To be removed) Inverse transfer function

netinv 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.

Syntax

A = netinv(N,FP)


Description

netinv is a transfer function. Transfer functions calculate a layer’s output from its net input.

A = netinv(N,FP) takes inputs

N	S-by-Q matrix of net input (column) vectors
FP	Struct of function parameters (ignored)

and returns 1/N.

info = netinv('code') returns information about this function. The following codes are supported:

netinv('name') returns the name of this function.

netinv('output',FP) returns the [min max] output range.

netinv('active',FP) returns the [min max] active input range.

netinv('fullderiv') returns 1 or 0, depending on whether dA_dN is S-by-S-by-Q or S-by-Q.

netinv('fpnames') returns the names of the function parameters.

netinv('fpdefaults') returns the default function parameters.

Examples

Here you define 10 five-element net input vectors N and calculate A.

n = rand(5,10);
a = netinv(n);

Assign this transfer function to layer i of a network.

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

Version History

Introduced in R2006a

R2026a: netinv will be removed

netinv 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.