Neural Network Toolbox™

Inverse transfer function

Syntax

• A = netinv(N,FP)
  dA_dN = netinv('dn',N,A,FP)
  info = netinv(code)
  

Description

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

netinv(N,FP) takes inputs

N	S x Q matrix of net input (column) vectors
FP	Structure of function parameters (ignored)

and returns 1/N.

netinv('dn',N,A,FP) returns the derivative of A with respect to N. If A or FP is not supplied or is set to [], FP reverts to the default parameters, and A is calculated from N.

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 x S x Q or S x 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';
  

See Also

tansig, logsig

Provide feedback about this page

negdist

netprod

© 1984-2008- The MathWorks, Inc.    -   Site Help   -   Patents   -   Trademarks   -   Privacy Policy   -   Preventing Piracy   -   RSS