AI-NNFlex

 view release on metacpan or  search on metacpan

CHANGES  view on Meta::CPAN

20050620

Fixed a bug in the implementation of bias weights. Implemented
the addition example.

##########################################################

0.23
20050424

changed sigmoid to sigmoid2 in mathlib - this is a sigmoid
function generally used in BPTT, which isn't yet implemented.

Replaced with a more standard 1/1+exp(1)**-x function.

Implemented Hopfield module.

###########################################################
0.22
XXXXXXXXX

examples/bp.pl  view on Meta::CPAN

        for(my $i = 0;$i<$numPatterns;$i++)
        {

            #select a pattern at random
            $patNum = (rand()*$numPatterns)-0.001;

            #calculate the current network output
            #and error for this pattern
            calcNet();

            #change network weights
            WeightChangesHO();
            WeightChangesIH();
        }

        #display the overall network error
        #after each epoch
        calcOverallError();

        print "epoch = ".$j."  RMS Error = ".$RMSerror."\n";

lib/AI/NNFlex.pm  view on Meta::CPAN

v0.11 introduces the lesion method, png support in the draw module and datasets.

v0.12 fixes a bug in reinforce.pm & adds a reflector in feedforward->run to make $network->run($dataset) work.

v0.13 introduces the momentum learning algorithm and fixes a bug that allowed training to proceed even if the node activation function module can't be loaded

v0.14 fixes momentum and backprop so they are no longer nailed to tanh hidden units only.

v0.15 fixes a bug in feedforward, and reduces the debug overhead

v0.16 changes some underlying addressing of weights, to simplify and speed  

v0.17 is a bugfix release, plus some cleaning of UI

v0.20 changes AI::NNFlex to be a base class, and ships three different network types (i.e. training algorithms). Backprop & momentum are both networks of the feedforward class, and inherit their 'run' method from feedforward.pm. 0.20 also fixes a who...

v0.21 cleans up the perldocs more, and makes nnflex more distinctly a base module. There are quite a number of changes in Backprop in the v0.21 distribution.

v0.22 introduces the ::connect method, to allow creation of recurrent connections, and manual control over connections between nodes/layers.

v0.23 includes a Hopfield module in the distribution.

v0.24 fixes a bug in the bias weight calculations

=head1 COPYRIGHT

Copyright (c) 2004-2005 Charles Colbourn. All rights reserved. This program is free software; you can redistribute it and/or modify it under the same terms as Perl itself.

lib/AI/NNFlex/Backprop.pm  view on Meta::CPAN

# Backprop with simple (non adaptive) momentum
##########################################################
# Versions
# ========
#
# 1.0	20050121	CColbourn	New module
# 1.1	20050201	CColbourn	Added call to activation
#					function slope instead
#					of hardcoded 1-y*y
#
# 1.2	20050218	CColbourn	Mod'd to change weight
#					indexing to array for
#					nnflex 0.16
#
# 1.3	20050307	CColbourn	packaged as a subclass of NNFLex
#
# 1.4	20050313	CColbourn	modified the slope function call
#					to avoid using eval
#
# 1.5	20050314	CColbourn	applied fahlman constant
# 					Renamed Backprop.pm, see CHANGES

lib/AI/NNFlex/Reinforce.pm  view on Meta::CPAN

# neuron.
#
##########################################################
# Versions
# ========
#
# 1.0	20041125	CColbourn	New module
# 1.1	20050116	CColbourn	Fixed reverse @layers
#					bug reported by GM Passos
#
# 1.2	20050218	CColbourn	Mod'd to change weight
#					addressing from hash to
#					array for nnf0.16
#
# 1.3	20050307	CColbourn	repackaged as a subclass
#					of nnflex
#
##########################################################
# ToDo
# ----
#