AI-NeuralNet-BackProp

 view release on metacpan or  search on metacpan

BackProp.pm  view on Meta::CPAN

if(0) {
       
       		# Formula by Steve Purkis
       		# Converges very fast for low-value inputs. Has trouble converging on high-value
       		# inputs. Feel free to play and try to get to work for high values.
			my $delta	=	$ammount * ($what - $value) * $self->{SYNAPSES}->{LIST}->[$i]->{INPUT};
			$self->{SYNAPSES}->{LIST}->[$i]->{WEIGHT}  +=  $delta;
			$self->{SYNAPSES}->{LIST}->[$i]->{PKG}->weight($ammount,$what);
}
			
			# This formula in use by default is original by me (Josiah Bryan) as far as I know.
			
			# If it is equal, then don't adjust
			#
			### Disabled because this soemtimes causes 
			### infinte loops when learning with range limits enabled
			#
			#next if($value eq $what);
			
			# Adjust increment by the weight of the synapse of 
			# this neuron & apply direction delta

Changes  view on Meta::CPAN

Revision history for Perl extension AI::NeuralNet::BackProp.

0.40  Fri Jul 21 02:19:50 2000
        - original version; created by Josiah Bryan

0.42  Wed Jul 26 05:30:19 2000
        - upgrade patch, by Josiah Bryan

0.77  Sat Aug 11 03:27:29 2000
        - major internal revision, by Josiah Bryan               

0.89  Thu Aug 17 03:01:11 2000
        - multiple minor revisions, by Josiah Bryan
        



( run in 0.674 second using v1.01-cache-2.11-cpan-f985c23238c )