Neural Network Toolbox™

Triangular basis transfer function

Graph and Symbol

Syntax

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

Description

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

tribas(N,FP) takes N and optional function parameters,

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

and returns A, an S x Q matrix of the triangular basis function applied to each element of N.

tribas('dn',N,A,FP) returns the S x Q 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.

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

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

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

tribas('fullderiv') returns 1 or 0, depending on whether dA_dN is S x S x Q or S x Q.

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

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

Examples

Here you create a plot of the tribas transfer function.

• n = -5:0.1:5;
  a = tribas(n);
  plot(n,a)
  

Assign this transfer function to layer i of a network.

• net.layers{i}.transferFcn = 'tribas';
  

Algorithm

• a = tribas(n) = 1 - abs(n), if -1 <= n <= 1
                = 0, otherwise
  

See Also

sim, radbas

Provide feedback about this page

trainscg

vec2ind

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