view release on metacpan or  search on metacpan

lib/AI/NeuralNet/Hopfield.pm  view on Meta::CPAN

			if ($value == 0) {
				$value += 2;
			}			
			$result->set($result_row, $result_col, $value);
		}
	}
	return $result;
}

sub add() {
	#weight matrix.
    my $matrix_a = shift;
	#identity matrix.
    my $matrix_b = shift;

	my $a_rows = $matrix_a->{_rows};
	my $a_cols = $matrix_a->{_cols};

	my $b_rows = $matrix_b->{_rows};
	my $b_cols = $matrix_b->{_cols};
	
	if ($a_rows != $b_rows) {
		die "To add the matrixes they must have the same number of rows and columns.";
	}

	if ($a_cols != $b_cols) {
		 die "To add the matrixes they must have the same number of rows and columns.";
	}

	my $result = Math::SparseMatrix->new($a_rows, $a_cols);

	for (my $result_row = 1; $result_row <= $a_rows; $result_row++) {
		for (my $result_col = 1; $result_col <= $a_cols; $result_col++) {
			my $value = $matrix_b->get($result_row, $result_col);			
			$result->set($result_row, $result_col, $matrix_a->get($result_row, $result_col) + $value  )
		}
	}
	return $result;
}

sub dot_product() {
	my $matrix_a = shift;
	my $matrix_b = shift;
	
	my $a_rows = $matrix_a->{_rows};
	my $a_cols = $matrix_a->{_cols};
	
	my $b_rows = $matrix_b->{_rows};
	my $b_cols = $matrix_b->{_cols};

	my @array_a = &packed_array($matrix_a);
	my @array_b = &packed_array($matrix_b);

	for (my $n = 0; $n <= $#array_b; $n++) {
		if ($array_b[$n] == 2) {
			$array_b[$n] = 0;
		}
	}
	
	if ($#array_a != $#array_b) {
		die "To take the dot product, both matrixes must be of the same length.";
	}

	my $result = 0;
	my $length = $#array_a + 1;

	for (my $i = 0; $i < $length; $i++) {
		$result += $array_a[$i] * $array_b[$i];
	}
	return $result;
}

sub packed_array() {
	my $matrix = shift;
	my @result = ();

	for (my $r = 1; $r <= $matrix->{_rows}; $r++) {
		for (my $c = 1; $c <= $matrix->{_cols}; $c++) {
			push(@result, $matrix->get($r, $c)); 
		}
	}
	return @result;
}

sub get_col() {
	my $self = shift;
	my $col  = shift;

	my $matrix = $self->matrix();
	
	my $matrix_rows = $self->matrix_rows();

	if ($col > $matrix_rows) {
		die "Can't get column";
	}

	my $new_matrix = Math::SparseMatrix->new($matrix_rows, 1);

	for (my $row = 1; $row <= $matrix_rows; $row++) {
		my $value = $matrix->get($row, $col);
		$new_matrix->set($row, 1, $value);
	}
	return $new_matrix;
}

sub print_matrix() {
    my $matrix  = shift;
    my $rs = $matrix->{_rows};
    my $cs = $matrix->{_cols};

	for (my $i = 1; $i <= $rs; $i++) {
		for (my $j = 1; $j <= $cs; $j++) {
			say "[$i,$j]" . $matrix->get($i, $j);
		}
	}
}

=head1 SYNOPSIS

This is a version of a Hopfield Network implemented in Perl. Hopfield networks are sometimes called associative networks since 
they associate a class pattern to each input pattern, they are tipically used for classification problems with binary pattern vectors.

=head1 SUBROUTINES/METHODS

=head2 New

In order to build new calssifiers, you have to pass to the constructor the number of rows and columns (neurons) for the matrix construction.