PRTools Contents

PRTools User Guide



Feed-forward neural net classifier back-end


 ALG Training algorithm: 'bpxnc' for back-propagation, 'lmnc'  for Levenberg-Marquardt
 A Training dataset
 UNITS Array indicating number of units in each hidden layer.  Default is a single hidden layer. Its size is the half of the  number of objects in A divided by feature size plus class size  (roughly half of the number of parameters to be optimised) with  a maximum of 100;
 ITER Number of iterations to train (default: inf)
 W_INI Weight initialisation network mapping (default: [], meaning  initialisation by Matlab's neural network toolbox)
 T Tuning set (default: [], meaning use A)
 FID File ID to write progress to (default [], see PRPROGRESS)

 W Trained feed-forward neural network mapping
 HIST Progress report (see below)


This function should not be called directly, but through one of its  front-ends, BPXNC or LMNC. Uses the Mathworks' Neural Network toolbox.

This routine escapes to KNNC if any class has less than 3 objects.

See also

mappings, datasets, bpxnc, lmnc, neurc, rnnc, rbnc, knnc,

PRTools Contents

PRTools User Guide

This file has been automatically generated. If badly readable, use the help-command in Matlab.