AI-NeuralNet-BackProp
view release on metacpan or search on metacpan
BackProp.pm view on Meta::CPAN
return $self->{OUTPUTS}->{LIST}->[$oid]->{ID};
}
1;
package AI::NeuralNet::BackProp;
use Benchmark;
use strict;
# Returns the number of elements in an array ref, undef on error
sub _FETCHSIZE {
my $a=$_[0];
my ($b,$x);
return undef if(substr($a,0,5) ne "ARRAY");
foreach $b (@{$a}) { $x++ };
return $x;
}
# Debugging subs
$AI::NeuralNet::BackProp::DEBUG = 0;
sub whowasi { (caller(1))[3] . '()' }
sub debug { shift; $AI::NeuralNet::BackProp::DEBUG = shift || 0; }
sub out1 { print shift() if ($AI::NeuralNet::BackProp::DEBUG eq 1) }
sub out2 { print shift() if (($AI::NeuralNet::BackProp::DEBUG eq 1) || ($AI::NeuralNet::BackProp::DEBUG eq 2)) }
sub out3 { print shift() if ($AI::NeuralNet::BackProp::DEBUG) }
sub out4 { print shift() if ($AI::NeuralNet::BackProp::DEBUG eq 4) }
# Rounds a floating-point to an integer with int() and sprintf()
sub intr {
shift if(substr($_[0],0,4) eq 'AI::');
try { return int(sprintf("%.0f",shift)) }
catch { return 0 }
}
# Used to format array ref into columns
# Usage:
# join_cols(\@array,$row_length_in_elements,$high_state_character,$low_state_character);
# Can also be called as method of your neural net.
# If $high_state_character is null, prints actual numerical values of each element.
sub join_cols {
no strict 'refs';
shift if(substr($_[0],0,4) eq 'AI::');
my $map = shift;
my $break = shift;
my $a = shift;
my $b = shift;
my $x;
foreach my $el (@{$map}) {
my $str = ((int($el))?$a:$b);
$str=$el."\0" if(!$a);
print $str;
$x++;
if($x>$break-1) {
print "\n";
$x=0;
}
}
print "\n";
}
# Returns percentage difference between all elements of two
# array refs of exact same length (in elements).
# Now calculates actual difference in numerical value.
sub pdiff {
no strict 'refs';
shift if(substr($_[0],0,4) eq 'AI::');
my $a1 = shift;
my $a2 = shift;
my $a1s = $#{$a1}; #AI::NeuralNet::BackProp::_FETCHSIZE($a1);
my $a2s = $#{$a2}; #AI::NeuralNet::BackProp::_FETCHSIZE($a2);
my ($a,$b,$diff,$t);
$diff=0;
#return undef if($a1s ne $a2s); # must be same length
for my $x (0..$a1s) {
$a = $a1->[$x];
$b = $a2->[$x];
if($a!=$b) {
if($a<$b){$t=$a;$a=$b;$b=$t;}
$a=1 if(!$a);
$diff+=(($a-$b)/$a)*100;
}
}
$a1s = 1 if(!$a1s);
return sprintf("%.10f",($diff/$a1s));
}
# Returns $fa as a percentage of $fb
sub p {
shift if(substr($_[0],0,4) eq 'AI::');
my ($fa,$fb)=(shift,shift);
sprintf("%.3f",((($fb-$fa)*((($fb-$fa)<0)?-1:1))/$fa)*100);
}
# This sub will take an array ref of a data set, which it expects in this format:
# my @data_set = ( [ ...inputs... ], [ ...outputs ... ],
# ... rows ...
# );
#
# This wil sub returns the percentage of 'forgetfullness' when the net learns all the
# data in the set in order. Usage:
#
# learn_set(\@data,[ options ]);
#
# Options are options in hash form. They can be of any form that $net->learn takes.
#
# It returns a percentage string.
#
sub learn_set {
my $self = shift if(substr($_[0],0,4) eq 'AI::');
my $data = shift;
my %args = @_;
my $len = $#{$data}/2-1;
my $inc = $args{inc};
my $max = $args{max};
my $error = $args{error};
my $p = (defined $args{flag}) ?$args{flag} :1;
my $row = (defined $args{pattern})?$args{pattern}*2+1:1;
my ($fa,$fb);
for my $x (0..$len) {
print "\nLearning index $x...\n" if($AI::NeuralNet::BackProp::DEBUG);
my $str = $self->learn( $data->[$x*2], # The list of data to input to the net
$data->[$x*2+1], # The output desired
inc=>$inc, # The starting learning gradient
max=>$max, # The maximum num of loops allowed
error=>$error); # The maximum (%) error allowed
print $str if($AI::NeuralNet::BackProp::DEBUG);
}
my $res;
$data->[$row] = $self->crunch($data->[$row]) if($data->[$row] == 0);
if ($p) {
$res=pdiff($data->[$row],$self->run($data->[$row-1]));
} else {
$res=$data->[$row]->[0]-$self->run($data->[$row-1])->[0];
}
return $res;
}
# This sub will take an array ref of a data set, which it expects in this format:
# my @data_set = ( [ ...inputs... ], [ ...outputs ... ],
# ... rows ...
# );
#
# This wil sub returns the percentage of 'forgetfullness' when the net learns all the
# data in the set in RANDOM order. Usage:
#
# learn_set_rand(\@data,[ options ]);
#
# Options are options in hash form. They can be of any form that $net->learn takes.
#
# It returns a true value.
#
sub learn_set_rand {
my $self = shift if(substr($_[0],0,4) eq 'AI::');
my $data = shift;
my %args = @_;
my $len = $#{$data}/2-1;
my $inc = $args{inc};
my $max = $args{max};
my $error = $args{error};
my @learned;
while(1) {
_GET_X:
my $x=$self->intr(rand()*$len);
goto _GET_X if($learned[$x]);
$learned[$x]=1;
print "\nLearning index $x...\n" if($AI::NeuralNet::BackProp::DEBUG);
my $str = $self->learn($data->[$x*2], # The list of data to input to the net
$data->[$x*2+1], # The output desired
inc=>$inc, # The starting learning gradient
max=>$max, # The maximum num of loops allowed
error=>$error); # The maximum (%) error allowed
print $str if($AI::NeuralNet::BackProp::DEBUG);
}
return 1;
}
# Returns the index of the element in array REF passed with the highest comparative value
sub high {
shift if(substr($_[0],0,4) eq 'AI::');
my $ref1 = shift;
my ($el,$len,$tmp);
foreach $el (@{$ref1}) {
$len++;
}
$tmp=0;
for my $x (0..$len-1) {
$tmp = $x if((@{$ref1})[$x] > (@{$ref1})[$tmp]);
}
return $tmp;
}
# Returns the index of the element in array REF passed with the lowest comparative value
sub low {
shift if(substr($_[0],0,4) eq 'AI::');
my $ref1 = shift;
my ($el,$len,$tmp);
foreach $el (@{$ref1}) {
$len++;
}
BackProp.pm view on Meta::CPAN
}
# Sets/gets column width for printing lists in debug modes 1,3, and 4.
sub col_width {
my $self = shift;
my $width = shift;
return $self->{col_width} if(!$width);
$self->{col_width} = $width;
}
# Sets/Removes value ranging
sub range {
my $self = shift;
my $ref = shift;
my $b = shift;
if(substr($ref,0,5) ne "ARRAY") {
if(($ref == 0) && (!defined $b)) {
$ref = $self->crunch($ref);
#print "\$ref is a string, crunching to ",join(',',@{$ref}),"\n";
} else {
my $a = $ref;
$a = $self->crunch($a)->[0] if($a == 0);
$b = $self->crunch($b)->[0] if($b == 0);
$_[++$#_] = $a;
$_[++$#_] = $b;
$ref = \@_;
#print "Found ranged definition, joined to ",join(',',@{$ref}),"\n";
}
}
my $rA = 0;
my $rB = $#{$ref};
my $rS = 0; #shift;
if(!$rA && !$rB) {
$self->{rA}=$self->{rB}=-1;
return undef;
}
if($rB<$rA){my $t=$rA;$rA=$rB;$rB=$t};
$self->{rA}=$rA;
$self->{rB}=$rB;
$self->{rS}=$rS if($rS);
$self->{rRef} = $ref;
return $ref;
}
# Used internally to scale outputs to fit range
sub _range {
my $self = shift;
my $in = shift;
my $rA = $self->{rA};
my $rB = $self->{rB};
my $rS = $self->{rS};
my $r = $rB;#-$rA+1;
return $in if(!$rA && !$rB);
my $l = $self->{OUT}-1;
my $out = [];
# Adjust for a maximum outside what we have seen so far
for my $i (0..$l) {
$rS=$in->[$i] if($in->[$i]>$rS);
}
#print "\$l:$l,\$rA:$rA,\$rB:$rB,\$rS:$rS,\$r:$r\n";
# Loop through, convert values to percentage of maximum, then multiply
# percentage by range and add to base of range to get finaly value
for my $i (0..$l) {
#print "\$i:$i,\$in:$in->[$i]\n";
$rS=1 if(!$rS);
my $t=intr((($rS-$in->[$i])/$rS)*$r+$rA);
#print "t:$t,$self->{rRef}->[$t],i:$i\n";
$out->[$i] = $self->{rRef}->[$t];
}
$self->{rS}=$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);
}
#print "Creating $size neurons in each layer for $layers layer(s)...\n";
AI::NeuralNet::BackProp::out2 "Creating $size neurons in each layer for $layers layer(s)...\n";
# Error checking
return undef if($out>$size);
# When this is called, they tell us howmany layers and neurons in each layer.
# But really what we store is a long line of neurons that are only divided in theory
# when connecting the outputs and inputs.
my $div = $size;
my $size = $layers * $size;
AI::NeuralNet::BackProp::out2 "Creating RUN and MAP systems for network...\n";
#print "Creating RUN and MAP systems for network...\n";
# Create a new runner and mapper for the network.
$self->{RUN} = new AI::NeuralNet::BackProp::_run($self);
$self->{MAP} = new AI::NeuralNet::BackProp::_map($self);
$self->{SIZE} = $size;
$self->{DIV} = $div;
$self->{OUT} = $out;
BackProp.pm view on Meta::CPAN
(Sorry about the bad art...I am no ASCII artist! :-)
B<1>
In addition to flag 0, each neuron in layer X is connected to every input of
the neurons ahead of itself in layer X.
B<2> I<("L-U Style")>
No, its not "Learning-Unit" style. It gets its name from this: In a 2 layer, 3
neuron network, the connections form a L-U pair, or a W, however you want to look
at it.
^ ^ ^
| | |
O-->O-->O
^ ^ ^
| | |
| | |
O-->O-->O
^ ^ ^
| | |
As you can see, each neuron is connected to the next one in its layer, as well
as the neuron directly above itself.
Before you can really do anything useful with your new neural network
object, you need to teach it some patterns. See the learn() method, below.
=item $net->learn($input_map_ref, $desired_result_ref [, options ]);
This will 'teach' a network to associate an new input map with a desired resuly.
It will return a string containg benchmarking information. You can retrieve the
pattern index that the network stored the new input map in after learn() is complete
with the pattern() method, below.
UPDATED: You can now specify strings as inputs and ouputs to learn, and they will be crunched
automatically. Example:
$net->learn('corn', 'cob');
# Before update, you have had to do this:
# $net->learn($net->crunch('corn'), $net->crunch('cob'));
Note, the old method of calling crunch on the values still works just as well.
UPDATED: You can now learn inputs with a 0 value. Beware though, it may not learn() a 0 value
in the input map if you have randomness disabled. See NOTES on using a 0 value with randomness
disabled.
The first two arguments may be array refs (or now, strings), and they may be of different lengths.
Options should be written on hash form. There are three options:
inc => $learning_gradient
max => $maximum_iterations
error => $maximum_allowable_percentage_of_error
$learning_gradient is an optional value used to adjust the weights of the internal
connections. If $learning_gradient is ommitted, it defaults to 0.20.
$maximum_iterations is the maximum numbers of iteration the loop should do.
It defaults to 1024. Set it to 0 if you never want the loop to quit before
the pattern is perfectly learned.
$maximum_allowable_percentage_of_error is the maximum allowable error to have. If
this is set, then learn() will return when the perecentage difference between the
actual results and desired results falls below $maximum_allowable_percentage_of_error.
If you do not include 'error', or $maximum_allowable_percentage_of_error is set to -1,
then learn() will not return until it gets an exact match for the desired result OR it
reaches $maximum_iterations.
=item $net->learn_set(\@set, [ options ]);
UPDATE: Inputs and outputs in the dataset can now be strings. See information on auto-crunching
in learn()
This takes the same options as learn() and allows you to specify a set to learn, rather
than individual patterns. A dataset is an array refrence with at least two elements in the
array, each element being another array refrence (or now, a scalar string). For each pattern to
learn, you must specify an input array ref, and an ouput array ref as the next element. Example:
my @set = (
# inputs outputs
[ 1,2,3,4 ], [ 1,3,5,6 ],
[ 0,2,5,6 ], [ 0,2,1,2 ]
);
See the paragraph on measuring forgetfulness, below. There are
two learn_set()-specific option tags available:
flag => $flag
pattern => $row
If "flag" is set to some TRUE value, as in "flag => 1" in the hash of options, or if the option "flag"
is not set, then it will return a percentage represting the amount of forgetfullness. Otherwise,
learn_set() will return an integer specifying the amount of forgetfulness when all the patterns
are learned.
If "pattern" is set, then learn_set() will use that pattern in the data set to measure forgetfulness by.
If "pattern" is omitted, it defaults to the first pattern in the set. Example:
my @set = (
[ 0,1,0,1 ], [ 0 ],
[ 0,0,1,0 ], [ 1 ],
[ 1,1,0,1 ], [ 2 ], # <---
[ 0,1,1,0 ], [ 3 ]
);
If you wish to measure forgetfulness as indicated by the line with the arrow, then you would
pass 2 as the "pattern" option, as in "pattern => 2".
Now why the heck would anyone want to measure forgetfulness, you ask? Maybe you wonder how I
even measure that. Well, it is not a vital value that you have to know. I just put in a
"forgetfulness measure" one day because I thought it would be neat to know.
How the module measures forgetfulness is this: First, it learns all the patterns in the set provided,
then it will run the very first pattern (or whatever pattern is specified by the "row" option)
in the set after it has finished learning. It will compare the run() output with the desired output
as specified in the dataset. In a perfect world, the two should match exactly. What we measure is
how much that they don't match, thus the amount of forgetfulness the network has.
NOTE: In version 0.77 percentages were disabled because of a bug. Percentages are now enabled.
Example (from examples/ex_dow.pl):
# Data from 1989 (as far as I know..this is taken from example data on BrainMaker)
my @data = (
# Mo CPI CPI-1 CPI-3 Oil Oil-1 Oil-3 Dow Dow-1 Dow-3 Dow Ave (output)
[ 1, 229, 220, 146, 20.0, 21.9, 19.5, 2645, 2652, 2597], [ 2647 ],
[ 2, 235, 226, 155, 19.8, 20.0, 18.3, 2633, 2645, 2585], [ 2637 ],
[ 3, 244, 235, 164, 19.6, 19.8, 18.1, 2627, 2633, 2579], [ 2630 ],
[ 4, 261, 244, 181, 19.6, 19.6, 18.1, 2611, 2627, 2563], [ 2620 ],
[ 5, 276, 261, 196, 19.5, 19.6, 18.0, 2630, 2611, 2582], [ 2638 ],
[ 6, 287, 276, 207, 19.5, 19.5, 18.0, 2637, 2630, 2589], [ 2635 ],
[ 7, 296, 287, 212, 19.3, 19.5, 17.8, 2640, 2637, 2592], [ 2641 ]
);
# Learn the set
my $f = learn_set(\@data,
inc => 0.1,
max => 500,
p => 1
);
# Print it
print "Forgetfullness: $f%";
This is a snippet from the example script examples/ex_dow.pl, which demonstrates DOW average
prediction for the next month. A more simple set defenition would be as such:
my @data = (
[ 0,1 ], [ 1 ],
[ 1,0 ], [ 0 ]
);
$net->learn_set(\@data);
Same effect as above, but not the same data (obviously).
=item $net->learn_set_rand(\@set, [ options ]);
UPDATE: Inputs and outputs in the dataset can now be strings. See information on auto-crunching
in learn()
This takes the same options as learn() and allows you to specify a set to learn, rather
than individual patterns.
learn_set_rand() differs from learn_set() 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.
Example:
my @data = (
[ 0,1 ], [ 1 ],
[ 1,0 ], [ 0 ]
);
$net->learn_set_rand(\@data);
BackProp.pm view on Meta::CPAN
This is the same as calling:
$net->range($net->crunch("first string"),$net->crunch("second string"));
Or:
@range = ($net->crunch("first string"),
$net->crunch("second string"));
$net->range(\@range);
=item $net->range($value1,$value2);
This is the same as calling:
$net->range([$value1,$value2]);
Or:
@range = ($value1,$value2);
$net->range(\@range);
The second example is the same as the first example.
=item $net->benchmarked();
UPDATE: bencmarked() now returns just the string from timestr() for the last run() or
loop() call. Exception: If the last call was a loop the string will be prefixed with "%d loops and ".
This returns a benchmark info string for the last learn() or the last run() call,
whichever occured later. It is easily printed as a string,
as following:
print $net->benchmarked() . "\n";
=item $net->debug($level)
Toggles debugging off if called with $level = 0 or no arguments. There are four levels
of debugging.
Level 0 ($level = 0) : Default, no debugging information printed. All printing is
left to calling script.
Level 1 ($level = 1) : This causes ALL debugging information for the network to be dumped
as the network runs. In this mode, it is a good idea to pipe your STDIO to a file, especially
for large programs.
Level 2 ($level = 2) : A slightly-less verbose form of debugging, not as many internal
data dumps.
Level 3 ($level = 3) : JUST prints weight mapping as weights change.
Level 4 ($level = 4) : JUST prints the benchmark info for EACH learn loop iteteration, not just
learning as a whole. Also prints the percentage difference for each loop between current network
results and desired results, as well as learning gradient ('incremenet').
Level 4 is useful for seeing if you need to give a smaller learning incrememnt to learn() .
I used level 4 debugging quite often in creating the letters.pl example script and the small_1.pl
example script.
Toggles debuging off when called with no arguments.
=item $net->save($filename);
This will save the complete state of the network to disk, including all weights and any
words crunched with crunch() . Also saves any output ranges set with range() .
This has now been modified to use a simple flat-file text storage format, and it does not
depend on any external modules now.
=item $net->load($filename);
This will load from disk any network saved by save() and completly restore the internal
state at the point it was save() was called at.
=item $net->join_cols($array_ref,$row_length_in_elements,$high_state_character,$low_state_character);
This is more of a utility function than any real necessary function of the package.
Instead of joining all the elements of the array together in one long string, like join() ,
it prints the elements of $array_ref to STDIO, adding a newline (\n) after every $row_length_in_elements
number of elements has passed. Additionally, if you include a $high_state_character and a $low_state_character,
it will print the $high_state_character (can be more than one character) for every element that
has a true value, and the $low_state_character for every element that has a false value.
If you do not supply a $high_state_character, or the $high_state_character is a null or empty or
undefined string, it join_cols() will just print the numerical value of each element seperated
by a null character (\0). join_cols() defaults to the latter behaviour.
=item $net->pdiff($array_ref_A, $array_ref_B);
This function is used VERY heavily internally to calculate the difference in percent
between elements of the two array refs passed. It returns a %.10f (sprintf-format)
percent sting.
=item $net->p($a,$b);
Returns a floating point number which represents $a as a percentage of $b.
=item $net->intr($float);
Rounds a floating-point number rounded to an integer using sprintf() and int() , Provides
better rounding than just calling int() on the float. Also used very heavily internally.
=item $net->high($array_ref);
Returns the index of the element in array REF passed with the highest comparative value.
=item $net->low($array_ref);
Returns the index of the element in array REF passed with the lowest comparative value.
=item $net->show();
This will dump a simple listing of all the weights of all the connections of every neuron
in the network to STDIO.
=item $net->crunch($string);
UPDATE: Now you can use a variabled instead of using qw(). Strings will be split internally.
Do not use qw() to pass strings to crunch.
This splits a string passed with /[\s\t]/ into an array ref containing unique indexes
to the words. The words are stored in an intenal array and preserved across load() and save()
calls. This is designed to be used to generate unique maps sutible for passing to learn() and
run() directly. It returns an array ref.
The words are not duplicated internally. For example:
$net->crunch("How are you?");
Will probably return an array ref containing 1,2,3. A subsequent call of:
$net->crunch("How is Jane?");
Will probably return an array ref containing 1,4,5. Notice, the first element stayed
the same. That is because it already stored the word "How". So, each word is stored
only once internally and the returned array ref reflects that.
=item $net->uncrunch($array_ref);
Uncrunches a map (array ref) into an scalar string of words seperated by ' ' and returns the
string. This is ment to be used as a counterpart to the crunch() method, above, possibly to
uncrunch() the output of a run() call. Consider the below code (also in ./examples/ex_crunch.pl):
use AI::NeuralNet::BackProp;
( run in 1.774 second using v1.01-cache-2.11-cpan-7fcb06a456a )