AI-NNFlex
view release on metacpan or search on metacpan
v0.17 was never released, as I rejigged the whole lot for
object inheritance before I got around to uploading it to CPAN.
Why? I hear you ask, when it worked OK already.
1) its faster, a lot faster.
2) feedforward isn't the only kind of network, and I wanted to
be free to overload some of the methods (especially init) to
simplify writing a Hopfield module (in progress)
3) its more theoretically correct
So now, AI::NNFlex is the base class for the other types of
networks, and you should never need to call AI::NNFlex class
directly - you should call the constructor of the subclass, such
as:
my $network = AI::NNFlex::momentum->new(params);
The upshot of that is that the network type and learning algorithm
parameters are now obsolete.
###
Removed draw.pm from the distribution - it really wasn't very useful
and hadn't been kept up to date with newer revisions of the code. It
will be put back later (perhaps) or incorporated into a separate GUI
frontend.
Removed feedforward_pdl.pm from the distribution - it shouldn't have
of an anonymous hash (left over from when I didn't know you could do
that).
Fixed an error - random weights was bounded by 1, not the parameter
'randomweights'. Its now positive only. Some benchmarking needed as
it appears that positive random starting weights rather than a mix
of positive and negative make the network quicker to converge, at
least with momentum.
weights now defaults to rand(1) instead of 0 - at least for backprop
type nets, a default 0 weight will never work. For other types of nets
the random weights can be overridden with the 'fixedweights' parameter.
Fixed load_state to correctly read weights from the bias node
#############################################################
examples/reinforceTest.pl view on Meta::CPAN
# this is /really/ experimental - see perldoc NNFlex::reinforce
use AI::NNFlex;
my $object = AI::NNFlex->new([{"nodes"=>2,"persistent activation"=>0,"decay"=>0.0,"random activation"=>0,"threshold"=>0.0,"activation function"=>"tanh","random weights"=>1},
{"nodes"=>2,"persistent activation"=>0,"decay"=>0.0,"random activation"=>0,"threshold"=>0.0,"activation function"=>"tanh","random weights"=>1},
{"nodes"=>1,"persistent activation"=>0,"decay"=>0.0,"random activation"=>0,"threshold"=>0.0,"activation function"=>"linear","random weights"=>1}],{'random connections'=>0,'networktype'=>'feedforward', 'random weights'=>1,'learn...
$object->run([1,0]);
$output = $object->output();
foreach (@$output)
{
print "1,0 - $_ ";
}
print "\n";
lib/AI/NNFlex.pm view on Meta::CPAN
#
# 0.16 20050218 CColbourn Changed from a hash of weights to an
# array of weights, to make it easier
# to adapt the code to PDL
#
# 0.17 20050302 CColbourn Changed input params to ::output to
# be param=>parameter not anon hash
# Included round parameter in output
#
# 0.20 20050307 CColbourn Modified for inheritance to simplify
# future network types
#
# 0.21 20050316 CColbourn Rewrote perldocs, implemented fahlman
# constant, chopped out old legacy stuff
# put math functions in mathlib, etc etc
#
# 0.22 20050317 CColbourn Implemented ::connect method
#
# 0.23 20050424 CColbourn Included Hopfield module in dist.
#
# 0.24 20050620 CColbourn Corrected a bug in the bias weight
lib/AI/NNFlex.pm view on Meta::CPAN
#
###############################################################################
# ToDo
# ====
#
# Modify init to allow recurrent layer/node connections
# write cmd & gui frontends
# Speed the bugger up!
#
# Odd thought - careful coding of a network would allow grafting of
# two different network types or learning algorithms, like an effectve
# single network with 2 layers unsupervised and 2 layers supervised
#
# Clean up the perldocs
#
###############################################################################
$VERSION = "0.24";
###############################################################################
my @DEBUG; # a single, solitary, shameful global variable. Couldn't
lib/AI/NNFlex.pm view on Meta::CPAN
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
lib/AI/NNFlex/Dataset.pm view on Meta::CPAN
# add an input/output pair to the dataset
##########################################################
sub add
{
my $dataset= shift;
my $params = shift;
if (!$params){return "Nothing to add"};
if ($params !~/ARRAY/){return "Need a reference to an array"}
# support adding single patterns (for Hopfield type nets)
if ($$params[0] !~ /ARRAY/)
{
push @{$dataset->{'data'}},$params;
}
else
{
push @{$dataset->{'data'}},$$params[0];
push @{$dataset->{'data'}},$$params[1];
}
lib/AI/NNFlex/Dataset.pm view on Meta::CPAN
$dataset->add([[0,1,0,1],[1,1,0,0]]);
$dataset->add([0,1,0,0]);
$dataset->save(filename=>'test.pat');
$dataset->load(filename=>'test.pat');
=head1 DESCRIPTION
This module allows you to construct, load, save and maintain datasets for use with neural nets implemented using the AI::NNFlex classes. The dataset consists of an array of references to arrays of data. Items may be added in pairs (useful for feedfor...
=head1 CONSTRUCTOR
=head2 AI::NNFlex::Dataset->new([[INPUT],[TARGET]]);
Parameters:
The constructor takes an (optional) reference to an array of one or more arrays. For convenience you can specify two values at a time (for INPUT and OUTPUT values) or a single value at a time. You can also leave the parameters blank, in which case th...
The return value is an AI::NNFlex::Dataset object.
lib/AI/NNFlex/Dataset.pm view on Meta::CPAN
$dataset->add([VALUE]);
This method adds new values to the end of the dataset. You can specify the values as pairs or individually.
=head2 load
Syntax:
$dataset->load(filename=>'filename.pat');
Loads an SNNS type .pat file into a blank dataset. If called on an existing dataset IT WILL OVERWRITE IT!
=head2 save
$dataset->save(filename=>'filename.pat');
Save the existing dataset as an SNNS .pat file. If the file already exists it will be overwritten.
=head2 delete
$dataset->delete(INDEX);
lib/AI/NNFlex/Feedforward.pm view on Meta::CPAN
###########################################################
# AI::NNFlex::Feedforward::run
###########################################################
#
#This class contains the run method only. The run method performs
#Feedforward (i.e. west to east) activation flow on the network.
#
#This class is internal to the NNFlex package, and is included
#in the NNFlex namespace by a require on the networktype parameter.
#
#syntax:
# $network->run([0,1,1,1,0,1,1]);
#
#
###########################################################
sub run
{
my $network = shift;
lib/AI/NNFlex/Mathlib.pm view on Meta::CPAN
Error functions
=over
=item *
atanh
=back
If you want to implement your own activation/error functions, you can add them to this module. All activation functions to be used by certain types of net (like Backprop) require an additional function <function name>_slope, which returns the 1st ord...
This rule doesn't apply to all network types. Hopfield for example requires no slope calculation.
=head1 CHANGES
v1.2 includes hopfield_threshold
=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.
=head1 CONTACT
( run in 2.314 seconds using v1.01-cache-2.11-cpan-df04353d9ac )