view release on metacpan or  search on metacpan

BackProp.pm  view on Meta::CPAN

	print $net->uncrunch($result),"\n";



=head1 UPDATES

This is version 0.89. In this version I have included a new feature, output range limits, as
well as automatic crunching of run() and learn*() inputs. Included in the examples directory
are seven new practical-use example scripts. Also implemented in this version is a much cleaner 
learning function for individual neurons which is more accurate than previous verions and is 
based on the LMS rule. See range() for information on output range limits. I have also updated 
the load() and save() methods so that they do not depend on Storable anymore. In this version 
you also have the choice between three network topologies, two not as stable, and the third is 
the default which has been in use for the previous four versions.


=head1 DESCRIPTION

AI::NeuralNet::BackProp implements a nerual network similar to a feed-foward,
back-propagtion network; learning via a mix of a generalization
of the Delta rule and a disection of Hebbs rule. The actual 

README  view on Meta::CPAN

From the POD:
This is version 0.89. In this version I have included a
new feature, output range limits, as well as automatic
crunching of run() and learn*() inputs. Included in the
examples directory are seven new practical-use example
scripts. Also implemented in this version is a much cleaner
learning function for individual neurons which is more
accurate than previous verions and is based on the LMS
rule. See range() for information on output range limits.
I have also updated the load() and save() methods so that
they do not depend on Storable anymore. In this version you
also have the choice between three network topologies, two
not as stable, and the third is the default which has been
in use for the previous four versions.

Checkout the nifty HTML-format docs in "docs.htm"

** What do you think?

Now I know you people are out there that are using the module...

docs.htm  view on Meta::CPAN

        print $net->uncrunch($result),"\n"
        
</PRE>        
<P>
<HR SIZE=1 COLOR=BLACK>
<H1><A NAME="updates">UPDATES</A></H1>
<P>This is version 0.89. In this version I have included a new feature, output range limits, as
well as automatic crunching of <A HREF="#item_run"><CODE>run()</CODE></A> and learn*() inputs. Included in the examples directory
are seven new practical-use example scripts. Also implemented in this version is a much cleaner 
learning function for individual neurons which is more accurate than previous verions and is 
based on the LMS rule. See <A HREF="#item_range"><CODE>range()</CODE></A> for information on output range limits. I have also updated 
the <A HREF="#item_load"><CODE>load()</CODE></A> and <A HREF="#item_save"><CODE>save()</CODE></A> methods so that they do not depend on Storable anymore. In this version 
you also have the choice between three network topologies, two not as stable, and the third is 
the default which has been in use for the previous four versions.</P>
<P>
<HR SIZE=1 COLOR=BLACK>
<H1><A NAME="description">DESCRIPTION</A></H1>
<P>AI::NeuralNet::BackProp implements a nerual network similar to a feed-foward,
back-propagtion network; learning via a mix of a generalization
of the Delta rule and a disection of Hebbs rule. The actual 
neruons of the network are implemented via the AI::NeuralNet::BackProp::neuron package.