view release on metacpan or  search on metacpan

docs.htm  view on Meta::CPAN

<PRE>
        my @data = (
                [ 0,1 ], [ 1 ],
                [ 1,0 ], [ 0 ]
        );

        $net-&gt;learn_set(\@data);
</PRE>
Same effect as above, but not the same data (obviously).
<P></P>
<DT><STRONG><A NAME="item_learn_set_rand">$net-&gt;learn_set_rand(\@set, [ options ]);</A></STRONG><BR>
<DD>
<B>UPDATED:</B> Inputs and outputs in the dataset can now be strings. See information on auto-crunching
in <A HREF="#item_learn"><CODE>learn()</CODE></A>
<P>This takes the same options as <A HREF="#item_learn"><CODE>learn()</CODE></A> and allows you to specify a set to learn, rather
than individual patterns.</P>
<P><A HREF="#item_learn_set_rand"><CODE>learn_set_rand()</CODE></A> differs from <A HREF="#item_learn_set"><CODE>learn_set()</CODE></A> in that it learns the patterns in a random order,
each pattern once, rather than in the order that they are in the array. This returns a true
value (1) instead of a forgetfullnes factor.</P>
<P>Example:</P>
<PRE>
        my @data = (
                [ 0,1 ], [ 1 ],
                [ 1,0 ], [ 0 ]
        );

        $net-&gt;learn_set_rand(\@data);</PRE>
<P></P>
<DT><STRONG><A NAME="item_run">$net-&gt;run($input_map_ref);</A></STRONG><BR>
<DD>
<B>UPDATED:</B> <A HREF="#item_run"><CODE>run()</CODE></A> will now <EM>automatically</EM> <A HREF="#item_crunch"><CODE>crunch()</CODE></A> a string given as the input.
<P>This method will apply the given array ref at the input layer of the neural network, and
it will return an array ref to the output of the network.</P>
<P>Example:
</P>
<PRE>

        my $inputs  = [ 1,1,0,1 ];
        my $outputs = $net-&gt;run($inputs);</PRE>
<P>With the new update you can do this:</P>
<PRE>
        my $outputs = $net-&gt;run('cloudy, wind is 5 MPH NW');
        # Old method:
        # my $outputs = $net-&gt;run($net-&gt;crunch('cloudy, wind is 5 MPH NW'));</PRE>
<P>See also <A HREF="#item_run_uc"><CODE>run_uc()</CODE></A> below.</P>
<P></P>
<DT><STRONG><A NAME="item_run_uc">$net-&gt;run_uc($input_map_ref);</A></STRONG><BR>
<DD>
This method does the same thing as this code:

<PRE>
        $net-&gt;uncrunch($net-&gt;run($input_map_ref));</PRE>
<P>All that <A HREF="#item_run_uc"><CODE>run_uc()</CODE></A> does is that it automatically calls <A HREF="#item_uncrunch"><CODE>uncrunch()</CODE></A> on the output, regardless
of whether the input was <A HREF="#item_crunch"><CODE>crunch()</CODE></A> -ed or not.</P>
<P></P>
<DT><STRONG><A NAME="item_range">$net-&gt;range();</A></STRONG><BR>
<DD>
This allows you to limit the possible outputs to a specific set of values. There are several 
ways you can specify the set of values to limit the output to. Each method is shown below. 
When called without any arguements, it will disable output range limits. You will need to re-learn
any data previously learned after disabling ranging, as disabling range invalidates the current
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>
<DT><STRONG>$net-&gt;range(``string of values'');</STRONG><BR>
<DD>
With this construct you can specify a string of values to be allowed as the outputs. This string
is simply taken an <A HREF="#item_crunch"><CODE>crunch()</CODE></A> -ed internally and saved as an array ref. This has the same effect
as calling:
<PRE>
        $net-&gt;range($net-&gt;crunch(&quot;string of values&quot;));</PRE>
<P></P>
<DT><STRONG>$net-&gt;range(``first string'',``second string'');</STRONG><BR>
<DD>
This is the same as calling:
<PRE>
        $net-&gt;range($net-&gt;crunch(&quot;first string&quot;),$net-&gt;crunch(&quot;second string&quot;));</PRE>
<P>Or:</P>
<PRE>
        @range = ($net-&gt;crunch(&quot;first string&quot;),
                          $net-&gt;crunch(&quot;second string&quot;));
        $net-&gt;range(\@range);</PRE>
<P></P>
<DT><STRONG>$net-&gt;range($value1,$value2);</STRONG><BR>
<DD>
This is the same as calling:
<PRE>
        $net-&gt;range([$value1,$value2]);</PRE>
<P>Or:
</P>
<PRE>

        @range = ($value1,$value2);
        $net-&gt;range(\@range);</PRE>
<P>The second example is the same as the first example.</P>
<P></P>
<DT><STRONG><A NAME="item_benchmarked">$net-&gt;benchmarked();</A></STRONG><BR>
<DD>
<B>UPDATED:</B> <CODE>bencmarked()</CODE> now returns just the string from <CODE>timestr()</CODE> for the last <A HREF="#item_run"><CODE>run()</CODE></A> or
<A HREF="#item_learn"><CODE>learn()</CODE></A> call. Exception: If the last call was a loop the string will be prefixed with ``%d loops and ''.
<P>This returns a benchmark info string for the last <A HREF="#item_learn"><CODE>learn()</CODE></A> or the last <A HREF="#item_run"><CODE>run()</CODE></A> call, 
whichever occured later. It is easily printed as a string,
as following:</P>
<PRE>
        print $net-&gt;benchmarked() . &quot;\n&quot;;</PRE>
<P></P>
<DT><STRONG><A NAME="item_debug">$net-&gt;debug($level)</A></STRONG><BR>
<DD>