RBNC

Trainable radial basis neural network classifier

    W = RBNC(A,UNITS)
    W = A*RBNC([],UNITS)
    W = A*RBNC(UNITS)

Input
A	Dataset
UNITS	Number of RBF units in hidden layer

Output
W	Radial basis neural network mapping

Description

A feed-forward neural network classifier with one hidden layer with  UNITS radial basis units is computed for labeled dataset A.  Default UNITS is number of objects * 0.2, but not more than 100.  Uses the Mathworks' Neural Network toolbox.

If UNITS is NaN it is optimised by REGOPTC. This may take a long  computing time and is often not significantly better than the default.

This routine escapes to KNNC for sample sizes < 6.

This routine calls MathWork's SOLVERB routine (Neural Network toolbox)  as SOLVB.

See also

mappings, datasets, lmnc, bpxnc, neurc, rnnc, regoptc,