The Complete SPRLIB & ANNLIB

dfpminimize

- perform the Broyden-Fletcher-Goldfarb-Shanno variant of the Davidon-Fletcher-Powell minimization algorithm (LOCAL)

SYNOPSIS

int dfpminimize (p, n, iter, verbose)

ARGUMENTS

double p[] Vector of all the weights present in the network.
int n Total number of trainable weights.
long iter Total number of iterations.
long verbose If TRUE this function will print the MSE during the iterations.

RETURNS

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

FUNCTION

Given a starting point p[1..n], Broyden-Fletcher-Goldfarb-Shanno minimization is performed on a the mean squared error, using its gradient as calculated by back propagation.

NOTE

This function is a modified version of the dfpmin() function found in NRinC.

SEE ALSO

learn_bfgs_ffnet

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