The Complete SPRLIB & ANNLIB

koh_learn

- perform a number of learning cycles with the Kohonen learning rule

SYNOPSIS

int koh_learn (net, dset, alpha, radius, cycles, options)

ARGUMENTS

NET *net A pointer to the NET structure under consideration.
DATASET *dset A pointer to a DATASET structure.
double alpha The learning rate.
double radius The radius of the region around the winning unit in which the units should be adapted.
long cycles The number of learning cycles to be performed.
long options A flag - see below (FUNCTION).

RETURNS

TRUE if an error was detected, FALSE otherwise.

FUNCTION

The function first checks a number of values: the net's NumInputs should match the dset 's NumInputs; cycles should be greater than 0; alpha should lie between -1.0 and 1.0 (not included) and radius should be greater than 0 but smaller than or equal to the number of network outputs net->NumOutputs. For each SAMPLE in dset with the SampleFlag set to SAMPLE_ENABLED (see SAMPLE-flags), the functions eval_ff_net and koh_adapt_net are called. The options parameter should be of type HIST-flags and KOHONEN-flags. The history flags are necessary for koh_adapt_unit; the Kohonen flag for koh_adapt_net.

NOTE

This function sets the net->ModificationDate field using the time_stamp function.

SEE ALSO

create_koh_net

This document was generated using api2html on Thu Mar 5 09:00:00 MET DST 1998