view release on metacpan or  search on metacpan

lib/AI/FANN.pm  view on Meta::CPAN

  FANN_LINEAR_PIECE_SYMMETRIC
  FANN_SIN_SYMMETRIC
  FANN_COS_SYMMETRIC
  FANN_SIN
  FANN_COS

  # enum fann_errorfunc_enum:
  FANN_ERRORFUNC_LINEAR
  FANN_ERRORFUNC_TANH

  # enum fann_stopfunc_enum:
  FANN_STOPFUNC_MSE
  FANN_STOPFUNC_BIT

=head1 CLASSES

The classes defined by this package are:

=head2 AI::FANN

Wraps C C<struct fann> types and provides the following methods
(consult the C documentation for a full description of their usage):

=over 4

=item AI::FANN->new_standard(@layer_sizes)

-

=item AI::FANN->new_sparse($connection_rate, @layer_sizes)

-

=item AI::FANN->new_shortcut(@layer_sizes)

-

=item AI::FANN->new_from_file($filename)

-

=item $ann->save($filename)

-

=item $ann->run($input)

C<input> is an array with the input values.

returns an array with the values on the output layer.

  $out = $ann->run([1, 0.6]);
  print "@$out\n";

=item $ann->randomize_weights($min_weight, $max_weight)

=item $ann->train($input, $desired_output)

C<$input> and C<$desired_output> are arrays.

=item $ann->test($input, $desired_output)

C<$input> and C<$desired_output> are arrays.

It returns an array with the values of the output layer.

=item $ann->reset_MSE

-

=item $ann->train_on_file($filename, $max_epochs, $epochs_between_reports, $desired_error)

-

=item $ann->train_on_data($train_data, $max_epochs, $epochs_between_reports, $desired_error)

C<$train_data> is a AI::FANN::TrainData object.

=item $ann->cascadetrain_on_file($filename, $max_neurons, $neurons_between_reports, $desired_error)

-

=item $ann->cascadetrain_on_data($train_data, $max_neurons, $neurons_between_reports, $desired_error)

C<$train_data> is a AI::FANN::TrainData object.

=item $ann->train_epoch($train_data)

C<$train_data> is a AI::FANN::TrainData object.

=item $ann->print_connections

-

=item $ann->print_parameters

-

=item $ann->cascade_activation_functions()

returns a list of the activation functions used for cascade training.

=item $ann->cascade_activation_functions(@activation_functions)

sets the list of activation function to use for cascade training.

=item $ann->cascade_activation_steepnesses()

returns a list of the activation steepnesses used for cascade training.

=item $ann->cascade_activation_steepnesses(@activation_steepnesses)

sets the list of activation steepnesses to use for cascade training.

=item $ann->training_algorithm

=item $ann->training_algorithm($training_algorithm)

-

=item $ann->train_error_function

lib/AI/FANN.pm  view on Meta::CPAN

=item AI::FANN::TrainData->new_empty($num_data, $num_inputs, $num_outputs)

returns a new AI::FANN::TrainData object of the sizes indicated on the
arguments. The initial values of the data contained inside the object
are random and should be set before using the train data object for
training an ANN.

=item $train->data($index)

returns two arrays with the values of the input and output layer
respectively for that index.

=item $train->data($index, $input, $output)

C<$input> and C<$output> are two arrays.

The input and output layers at the index C<$index> are set to the
values on these arrays.

=item $train->shuffle

-

=item $train->scale_input($new_min, $new_max)

-

=item $train->scale_output($new_min, $new_max)

-

=item $train->scale($new_min, $new_max)

-

=item $train->subset($pos, $length)

-

=item $train->num_inputs

-

=item $train->num_outputs

-

=item $train->length

-

=back

=head1 INSTALLATION

See the README file for instruction on installing this module.

=head1 BUGS

Only tested on Linux.

I/O is not performed through PerlIO because the C library doesn't have
the required infrastructure to do that.

Send bug reports to my email address or use the CPAN RT system.

=head1 SEE ALSO

FANN homepage at L<http://leenissen.dk/fann/index.php>.

=head1 COPYRIGHT AND LICENSE

Copyright (C) 2006-2008 by Salvador FandiE<ntilde>o
(sfandino@yahoo.com).

This Perl module is free software; you can redistribute it and/or
modify it under the same terms as Perl itself, either Perl version
5.8.8 or, at your option, any later version of Perl 5 you may have
available.

The Fast Artificial Neural Network Library (FANN)
Copyright (C) 2003-2006 Steffen Nissen (lukesky@diku.dk) and others.

Distributed under the GNU Lesser General Public License.

=cut