AI-NeuralNet-BackProp

 view release on metacpan or  search on metacpan

BackProp.pm  view on Meta::CPAN

		$self->{rS}=$rS;
		return $out;
	}
			
		
	# Initialzes the base for a new neural network.
	# It is recomended that you call learn() before run()ing a pattern.
	# See documentation above for usage.
	sub new {
    	no strict;
    	my $type	=	shift;
		my $self	=	{};
		my $layers	=	shift;
		my $size	=	shift;
		my $out		=	shift || $size;
		my $flag	=	shift || 0;
		
		bless $self, $type;
		
		# If $layers is a string, then it will be nummerically equal to 0, so try to load it
		# as a network file.
		if($layers == 0) {  
		    # We use a "1" flag as the second argument to indicate that we want load()
		    # to call the new constructor to make a network the same size as in the file
		    # and return a refrence to the network, instead of just creating the network from
		    # pre-exisiting refrence
			return $self->load($layers,1);
		}

BackProp.pm  view on Meta::CPAN

		my $ret=\@map;
		return $self->{PARENT}->_range($ret);
	}
1;
			      
# load_pcx() wrapper package
package AI::NeuralNet::BackProp::PCX;

	# Called by load_pcx in AI::NeuralNet::BackProp;
	sub new {
		my $type	=	shift;
		my $self	=	{ 
			parent  => $_[0],
			file    => $_[1]
		};
		my (@a,@b)=load_pcx($_[1]);
		$self->{image}=\@a;
		$self->{palette}=\@b;
		bless \%{$self}, $type;
	}

	# Returns a rectangular block defined by an array ref in the form of
	# 		[$x1,$y1,$x2,$y2]
	# Return value is an array ref
	sub get_block {
		my $self	=	shift;
		my $ref		=	shift;
		my ($x1,$y1,$x2,$y2)	=	@{$ref};
		my @block	=	();

BackProp.pm  view on Meta::CPAN

the whole data set again after calling range() on a network.

Subsequent calls to range() invalidate any previous calls to range()

NOTE: It is recomended, you call range() before you call learn() or else you will get unexpected
results from any run() call after range() .


=item $net->range($bottom..$top);

This is a common form often used in a C<for my $x (0..20)> type of for() constructor. It works
the exact same way. It will allow all numbers from $bottom to $top, inclusive, to be given 
as outputs of the network. No other values will be possible, other than those between $bottom
and $top, inclusive.


=item $net->range(\@values);

This allows you to specify a range of values as an array refrence. As the ranges are stored internally
as a refrence, this is probably the most natural way. Any value specified by an element in @values
will be allows as an output, no other values will be allowed.

docs.htm  view on Meta::CPAN

weight matrix in the network.
<P><A HREF="#item_range"><CODE>range()</CODE></A> automatically scales the networks outputs to fit inside the size of range you allow, and, therefore,
it keeps track of the maximum output it can expect to scale. Therefore, you will need to <A HREF="#item_learn"><CODE>learn()</CODE></A> 
the whole data set again after calling <A HREF="#item_range"><CODE>range()</CODE></A> on a network.</P>
<P>Subsequent calls to <A HREF="#item_range"><CODE>range()</CODE></A> invalidate any previous calls to <A HREF="#item_range"><CODE>range()</CODE></A></P>
<P>NOTE: It is recomended, you call <A HREF="#item_range"><CODE>range()</CODE></A> before you call <A HREF="#item_learn"><CODE>learn()</CODE></A> or else you will get unexpected
results from any <A HREF="#item_run"><CODE>run()</CODE></A> call after <A HREF="#item_range"><CODE>range()</CODE></A> .</P>
<P></P>
<DT><STRONG>$net-&gt;range($bottom..$top);</STRONG><BR>
<DD>
This is a common form often used in a <CODE>for my $x (0..20)</CODE> type of <CODE>for()</CODE> constructor. It works
the exact same way. It will allow all numbers from $bottom to $top, inclusive, to be given 
as outputs of the network. No other values will be possible, other than those between $bottom
and $top, inclusive.
<P></P>
<DT><STRONG>$net-&gt;range(\@values);</STRONG><BR>
<DD>
This allows you to specify a range of values as an array refrence. As the ranges are stored internally
as a refrence, this is probably the most natural way. Any value specified by an element in @values
will be allows as an output, no other values will be allowed.
<P></P>

examples/ex_alpha.pl  view on Meta::CPAN

	use AI::NeuralNet::BackProp;

	# Create a new network with 2 layers and 35 neurons in each layer, with 1 output neuron
	my $net = new AI::NeuralNet::BackProp(2,35,1);
	
	# Debug level of 4 gives JUST learn loop iteteration benchmark and comparrison data 
	# as learning progresses.
	$net->debug(4);

	my $letters = [            # All prototype inputs        
        [
        2,1,1,1,2,             # Inputs are   
        1,2,2,2,1,             #  5*7 digitalized caracters 
        1,2,2,2,1,              
        1,1,1,1,1,
        1,2,2,2,1,             # This is the alphabet of the
        1,2,2,2,1,             # HP 28S                      
        1,2,2,2,1,
        ],[0],[
        1,1,1,1,2,