NEURC

Automatic neural network classifier with one hidden layer

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

Input
A	Dataset

Output
W	Trained feed-forward neural network mapping
UNITS	Number of hidden units used.

Description

Automatically trained feed-forward neural network classifier. All  parameters are automatically determined. The number of hidden units is  the number of objects of A divided by the number of classes plus the  feature size, but at least 2 and at most 100.

The network is initialised by RNNC and trained by LMNC. Training is  stopped when the performance measured by an automatically generated  tuning set of 1000 objects does not improve anymore or after the time set  by PRTIME.

Uses the Mathworks' neural network toolbox.

This routine escapes to KNNC if no classes have more than 2 objects.

See also

mappings, datasets, lmnc, bpxnc, gendatk, regoptc, prtime,