view release on metacpan or  search on metacpan

lib/AI/FANN.pm  view on Meta::CPAN

=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

=item $ann->train_error_function($error_function)

-

=item $ann->train_stop_function

=item $ann->train_stop_function($stop_function)

-

=item $ann->learning_rate

=item $ann->learning_rate($rate)

-

=item $ann->learning_momentum

=item $ann->learning_momentum($momentun)

-

=item $ann->bit_fail_limit

=item $ann->bit_fail_limit($bfl)

-

=item $ann->quickprop_decay

=item $ann->quickprop_decay($qpd)

-

=item $ann->quickprop_mu

=item $ann->quickprop_mu($qpmu)

-

=item $ann->rprop_increase_factor

=item $ann->rprop_increase_factor($factor)

-

=item $ann->rprop_decrease_factor

=item $ann->rprop_decrease_factor($factor)

-

=item $ann->rprop_delta_min

=item $ann->rprop_delta_min($min)

-

=item $ann->rprop_delta_max

=item $ann->rprop_delta_max($max)

-

=item $ann->num_inputs

-

=item $ann->num_outputs

-

=item $ann->total_neurons

-

=item $ann->total_connections

-

=item $ann->MSE

-

=item $ann->bit_fail

-

=item cascade_output_change_fraction

=item cascade_output_change_fraction($fraction)

-

=item $ann->cascade_output_stagnation_epochs

=item $ann->cascade_output_stagnation_epochs($epochs)

-

=item $ann->cascade_candidate_change_fraction

=item $ann->cascade_candidate_change_fraction($fraction)

-

=item $ann->cascade_candidate_stagnation_epochs

=item $ann->cascade_candidate_stagnation_epochs($epochs)

-

=item $ann->cascade_weight_multiplier

=item $ann->cascade_weight_multiplier($multiplier)

-

=item $ann->cascade_candidate_limit

=item $ann->cascade_candidate_limit($limit)

-

=item $ann->cascade_max_out_epochs

=item $ann->cascade_max_out_epochs($epochs)

-

=item $ann->cascade_max_cand_epochs

=item $ann->cascade_max_cand_epochs($epochs)

-

=item $ann->cascade_num_candidates

-

=item $ann->cascade_num_candidate_groups

=item $ann->cascade_num_candidate_groups($groups)

-

=item $ann->neuron_activation_function($layer_index, $neuron_index)

=item $ann->neuron_activation_function($layer_index, $neuron_index, $activation_function)

-

=item $ann->layer_activation_function($layer_index, $activation_function)

-

=item $ann->hidden_activation_function($layer_index, $activation_function)

-

=item $ann->output_activation_function($layer_index, $activation_function)

-

=item $ann->neuron_activation_steepness($layer_index, $neuron_index)

=item $ann->neuron_activation_steepness($layer_index, $neuron_index, $activation_steepness)

-

=item $ann->layer_activation_steepness($layer_index, $activation_steepness)

-

=item $ann->hidden_activation_steepness($layer_index, $activation_steepness)

-

=item $ann->output_activation_steepness($layer_index, $activation_steepness)

-

=item $ann->num_layers

returns the number of layers on the ANN

=item $ann->layer_num_neurons($layer_index)

return the number of neurons on layer C<$layer_index>.

=item $ann->num_neurons

return a list with the number of neurons on every layer

=back

=head2 AI::FANN::TrainData

Wraps C C<struct fann_train_data> and provides the following method:

=over 4

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