The Complete SPRLIB & ANNLIB

pn_adapt_net

- perform one learning cycle with the pseudo-Newton variation of backpropagation

SYNOPSIS

int pn_adapt_net (net, eta, alpha, mu, target, options)

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.
double mu A small constant used in diverting inflection points in the pseudo-Newton method.
double *target The target output vector.
long options See note in pn_adapt_unit.

RETURNS

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

FUNCTION

The pn_adapt_unit function is called for all UNITs in net. If the network is a shared weights network (NetFlag = SHAREDNET) however, that function is only called for all units in the output layer, after which the pn_adapt_weights function is called. This procedure is repeated for the preceding layer, and so on until the first layer is reached.

NOTE

For an explanation of the possible values of options, see the note in pn_adapt_unit.

SEE ALSO

pn_learn

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