AI-NeuralNet-BackProp
1 match

 view release on metacpan or  search on metacpan

docs.htm  view on Meta::CPAN 

<HTML>
<HEAD>
<TITLE>AI::NeuralNet::BackProp - A simple back-prop neural net that uses Delta's and Hebbs' rule.</TITLE>
<LINK REV="made" HREF="mailto:">
<STYLE>
	BODY { font-family:Verdana; font-size:11; color:black; }
	CODE { background: rgb(200,200,200); }
	PRE	 { background:rgb(220,220,220); padding: 5; border:1px black solid; }
	A:link    {font-family:Verdana, Arial, Helvetica, Helv; font-size:10px; text-decoration:underline; font-weight:normal; color:rgb(58,73,114);}
	A:visited {font-family:Verdana, Arial, Helvetica, Helv; font-size:10px; text-decoration:normal; font-weight:normal; color:rgb(58,73,114);}
	A:hover   {font-family:Verdana, Arial, Helvetica, Helv; font-size:10px; text-decoration:underline; font-weight:normal; color:rgb(200,50,0);}
</STYLE>
</HEAD>

<BODY>

<PRE>
AI::NeuralNet::BackProp - A simple back-prop neural net that uses Delta's and Hebbs' rule.</TITLE>
</PRE>

<HR SIZE=1 COLOR=BLACK>

<A NAME="__index__"></A>
<!-- INDEX BEGIN -->

<UL>

	<LI><A HREF="#name">NAME</A></LI>
	<LI><A HREF="#synopsis">SYNOPSIS</A></LI>
	<LI><A HREF="#updates">UPDATES</A></LI>
	<LI><A HREF="#description">DESCRIPTION</A></LI>
	<UL>
        <LI><A HREF="#methods">METHODS</A></LI>
	</UL>

	<LI><A HREF="#notes">NOTES</A></LI>
	<LI><A HREF="#other included packages">OTHER INCLUDED PACKAGES</A></LI>
	<LI><A HREF="#bugs">BUGS</A></LI>
	<LI><A HREF="#author">AUTHOR</A></LI>
	<LI><A HREF="#thanks">THANKS</A></LI>
	<LI><A HREF="#download">DOWNLOAD</A></LI>
	<LI><A HREF="#mailing list">MAILING LIST</A></LI>
	<LI><A HREF="#what can it do">WHAT CAN IT DO?</A></LI>
</UL>
<!-- INDEX END -->

<HR SIZE=1 COLOR=BLACK>
<P>
<H1><A NAME="name">NAME</A></H1>
<P>AI::NeuralNet::BackProp - A simple back-prop neural net that uses Delta's and Hebbs' rule.</P>
<P>
<HR SIZE=1 COLOR=BLACK>
<H1><A NAME="synopsis">SYNOPSIS</A></H1>
<PRE>
        use AI::NeuralNet::BackProp;

        # Create a new network with 1 layer, 5 inputs, and 5 outputs.
        my $net = new AI::NeuralNet::BackProp(1,5,5);

        # Add a small amount of randomness to the network
        $net-&gt;random(0.001);
        # Demonstrate a simple learn() call
        my @inputs = ( 0,0,1,1,1 );
        my @ouputs = ( 1,0,1,0,1 );

        print $net-&gt;learn(\@inputs, \@outputs),&quot;\n&quot;;

        # Create a data set to learn



( run in 2.024 seconds using v1.01-cache-2.11-cpan-d8267643d1d )