The Complete SPRLIB & ANNLIB

samann_adapt_net

- perform one learning cycle using the SAMANN rule

SYNOPSIS

int samann_adapt_net (net, eta, alpha, options, pass, lamda, set_dist, map_dist)

ARGUMENTS

NET *net A pointer to a NET.
double eta The coefficient eta (the learning rate) of the backpropagation rule.
double alpha The coefficient alpha (the momentum term) of the backpropagation rule.
long options See note below.
int pass The pass for which this function is called: 1 or 2 - see below.
double lambda The Sammon constant - see samann_lambda.
double set_dist The distance in the original set between the sample shown in pass 1 and that shown in pass 2.
double map_dist The current distance in the map between the sample shown in pass 1 and that shown in pass 2.

RETURNS

TRUE if an error was detected, FALSE if no error was detected.

FUNCTION

If pass = 1, various parameters in each UNIT's SAMANN_STRUCT structure are reset to 0 (CurError, AccumDelta). The samann_adapt_unit function is called for each UNIT in net.

NOTE

In the options-parameter the following flags are to be specified:
HISTU (Don't) store history of unit values at each update.
HISTT (Don't) store history of unit thetas at each update.
HISTW (Don't) store history of weights at each update.
SAACCUM (Don't) accumulate the delta's.
SAUPDATE (Don't) update the weights.
SAOLDPRP (Don't) backpropagate using the original weights (i.e., the weights as they were before this update of the network).

See samann_adapt_unit for an explanation of the possible flag combinations. This function is used by samann_learn_sample.

SEE ALSO

samann_adapt_unit, samann_learn_sample

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