FANN Cascade Training

Cascade training differs from ordinary training in the sense that it starts with an empty neural network and then adds neurons one by one, while it trains the neural network.  The main benefit of this approach is that you do not have to guess the number of hidden layers and neurons prior to training, but cascade training has also proved better at solving some problems.

The basic idea of cascade training is that a number of candidate neurons are trained separate from the real network, then the most promising of these candidate neurons is inserted into the neural network.  Then the output connections are trained and new candidate neurons are prepared.  The candidate neurons are created as shortcut connected neurons in a new hidden layer, which means that the final neural network will consist of a number of hidden layers with one shortcut connected neuron in each.

Summary
FANN Cascade TrainingCascade training differs from ordinary training in the sense that it starts with an empty neural network and then adds neurons one by one, while it trains the neural network.
Cascade Training
fann_cascadetrain_on_dataTrains on an entire dataset, for a period of time using the Cascade2 training algorithm.
fann_cascadetrain_on_fileDoes the same as fann_cascadetrain_on_data, but reads the training data directly from a file.
Parameters
fann_get_cascade_output_change_fractionThe cascade output change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_output_stagnation_epochs during training of the output connections, in order for the training not to stagnate.
fann_set_cascade_output_change_fractionSets the cascade output change fraction.
fann_get_cascade_output_stagnation_epochsThe number of cascade output stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_output_change_fraction.
fann_set_cascade_output_stagnation_epochsSets the number of cascade output stagnation epochs.
fann_get_cascade_candidate_change_fractionThe cascade candidate change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_candidate_stagnation_epochs during training of the candidate neurons, in order for the training not to stagnate.
fann_set_cascade_candidate_change_fractionSets the cascade candidate change fraction.
fann_get_cascade_candidate_stagnation_epochsThe number of cascade candidate stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_candidate_change_fraction.
fann_set_cascade_candidate_stagnation_epochsSets the number of cascade candidate stagnation epochs.
fann_get_cascade_weight_multiplierThe weight multiplier is a parameter which is used to multiply the weights from the candidate neuron before adding the neuron to the neural network.
fann_set_cascade_weight_multiplierSets the weight multiplier.
fann_get_cascade_candidate_limitThe candidate limit is a limit for how much the candidate neuron may be trained.
fann_set_cascade_candidate_limitSets the candidate limit.
fann_get_cascade_max_out_epochsThe maximum out epochs determines the maximum number of epochs the output connections may be trained after adding a new candidate neuron.
fann_set_cascade_max_out_epochsSets the maximum out epochs.
fann_get_cascade_min_out_epochsThe minimum out epochs determines the minimum number of epochs the output connections must be trained after adding a new candidate neuron.
fann_set_cascade_min_out_epochsSets the minimum out epochs.
fann_get_cascade_max_cand_epochsThe maximum candidate epochs determines the maximum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.
fann_set_cascade_max_cand_epochsSets the max candidate epochs.
fann_get_cascade_min_cand_epochsThe minimum candidate epochs determines the minimum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.
fann_set_cascade_min_cand_epochsSets the min candidate epochs.
fann_get_cascade_num_candidatesThe number of candidates used during training (calculated by multiplying fann_get_cascade_activation_functions_count, fann_get_cascade_activation_steepnesses_count and fann_get_cascade_num_candidate_groups).
fann_get_cascade_activation_functions_countThe number of activation functions in the fann_get_cascade_activation_functions array.
fann_get_cascade_activation_functionsThe cascade activation functions array is an array of the different activation functions used by the candidates.
fann_set_cascade_activation_functionsSets the array of cascade candidate activation functions.
fann_get_cascade_activation_steepnesses_countThe number of activation steepnesses in the fann_get_cascade_activation_functions array.
fann_get_cascade_activation_steepnessesThe cascade activation steepnesses array is an array of the different activation functions used by the candidates.
fann_set_cascade_activation_steepnessesSets the array of cascade candidate activation steepnesses.
fann_get_cascade_num_candidate_groupsThe number of candidate groups is the number of groups of identical candidates which will be used during training.
fann_set_cascade_num_candidate_groupsSets the number of candidate groups.

Cascade Training

fann_cascadetrain_on_data

FANN_EXTERNAL void FANN_API fann_cascadetrain_on_data(
   struct fann *ann,
   struct fann_train_data *data,
   unsigned int max_neurons,
   unsigned int neurons_between_reports,
   float desired_error
)

Trains on an entire dataset, for a period of time using the Cascade2 training algorithm.  This algorithm adds neurons to the neural network while training, which means that it needs to start with an ANN without any hidden layers.  The neural network should also use shortcut connections, so fann_create_shortcut should be used to create the ANN like this:

struct fann *ann = fann_create_shortcut(2, fann_num_input_train_data(train_data), fann_num_output_train_data(train_data));

This training uses the parameters set using the fann_set_cascade_..., but it also uses another training algorithm as it’s internal training algorithm.  This algorithm can be set to either FANN_TRAIN_RPROP or FANN_TRAIN_QUICKPROP by fann_set_training_algorithm, and the parameters set for these training algorithms will also affect the cascade training.

Parameters

annThe neural network
dataThe data, which should be used during training
max_neuronThe maximum number of neurons to be added to neural network
neurons_between_reportsThe number of neurons between printing a status report to stdout.  A value of zero means no reports should be printed.
desired_errorThe desired fann_get_MSE or fann_get_bit_fail, depending on which stop function is chosen by fann_set_train_stop_function.

Instead of printing out reports every neurons_between_reports, a callback function can be called (see fann_set_callback).

See also

fann_train_on_data, fann_cascadetrain_on_file, Parameters

This function appears in FANN >= 2.0.0.

fann_cascadetrain_on_file

FANN_EXTERNAL void FANN_API fann_cascadetrain_on_file(
   struct fann *ann,
   const char *filename,
   unsigned int max_neurons,
   unsigned int neurons_between_reports,
   float desired_error
)

Does the same as fann_cascadetrain_on_data, but reads the training data directly from a file.

See also

fann_cascadetrain_on_data

This function appears in FANN >= 2.0.0.

Parameters

fann_get_cascade_output_change_fraction

FANN_EXTERNAL float FANN_API fann_get_cascade_output_change_fraction(
   struct fann *ann
)

The cascade output change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_output_stagnation_epochs during training of the output connections, in order for the training not to stagnate.  If the training stagnates, the training of the output connections will be ended and new candidates will be prepared.

This means

If the MSE does not change by a fraction of fann_get_cascade_output_change_fraction during a period of fann_get_cascade_output_stagnation_epochs, the training of the output connections is stopped because the training has stagnated.

If the cascade output change fraction is low, the output connections will be trained more and if the fraction is high they will be trained less.

The default cascade output change fraction is 0.01, which is equivalent to a 1% change in MSE.

See also

fann_set_cascade_output_change_fraction, fann_get_MSE, fann_get_cascade_output_stagnation_epochs

This function appears in FANN >= 2.0.0.

fann_set_cascade_output_change_fraction

FANN_EXTERNAL void FANN_API fann_set_cascade_output_change_fraction(
   struct fann *ann,
   float cascade_output_change_fraction
)

Sets the cascade output change fraction.

See also

fann_get_cascade_output_change_fraction

This function appears in FANN >= 2.0.0.

fann_get_cascade_output_stagnation_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_output_stagnation_epochs(
   struct fann *ann
)

The number of cascade output stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_output_change_fraction.

See more info about this parameter in fann_get_cascade_output_change_fraction.

The default number of cascade output stagnation epochs is 12.

See also

fann_set_cascade_output_stagnation_epochs, fann_get_cascade_output_change_fraction

This function appears in FANN >= 2.0.0.

fann_set_cascade_output_stagnation_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_output_stagnation_epochs(
   struct fann *ann,
   unsigned int cascade_output_stagnation_epochs
)

Sets the number of cascade output stagnation epochs.

See also

fann_get_cascade_output_stagnation_epochs

This function appears in FANN >= 2.0.0.

fann_get_cascade_candidate_change_fraction

FANN_EXTERNAL float FANN_API fann_get_cascade_candidate_change_fraction(
   struct fann *ann
)

The cascade candidate change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_candidate_stagnation_epochs during training of the candidate neurons, in order for the training not to stagnate.  If the training stagnates, the training of the candidate neurons will be ended and the best candidate will be selected.

This means

If the MSE does not change by a fraction of fann_get_cascade_candidate_change_fraction during a period of fann_get_cascade_candidate_stagnation_epochs, the training of the candidate neurons is stopped because the training has stagnated.

If the cascade candidate change fraction is low, the candidate neurons will be trained more and if the fraction is high they will be trained less.

The default cascade candidate change fraction is 0.01, which is equivalent to a 1% change in MSE.

See also

fann_set_cascade_candidate_change_fraction, fann_get_MSE, fann_get_cascade_candidate_stagnation_epochs

This function appears in FANN >= 2.0.0.

fann_set_cascade_candidate_change_fraction

FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_change_fraction(
   struct fann *ann,
   float cascade_candidate_change_fraction
)

Sets the cascade candidate change fraction.

See also

fann_get_cascade_candidate_change_fraction

This function appears in FANN >= 2.0.0.

fann_get_cascade_candidate_stagnation_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_candidate_stagnation_epochs(
   struct fann *ann
)

The number of cascade candidate stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_candidate_change_fraction.

See more info about this parameter in fann_get_cascade_candidate_change_fraction.

The default number of cascade candidate stagnation epochs is 12.

See also

fann_set_cascade_candidate_stagnation_epochs, fann_get_cascade_candidate_change_fraction

This function appears in FANN >= 2.0.0.

fann_set_cascade_candidate_stagnation_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_stagnation_epochs(
   struct fann *ann,
   unsigned int cascade_candidate_stagnation_epochs
)

Sets the number of cascade candidate stagnation epochs.

See also

fann_get_cascade_candidate_stagnation_epochs

This function appears in FANN >= 2.0.0.

fann_get_cascade_weight_multiplier

FANN_EXTERNAL fann_type FANN_API fann_get_cascade_weight_multiplier(
   struct fann *ann
)

The weight multiplier is a parameter which is used to multiply the weights from the candidate neuron before adding the neuron to the neural network.  This parameter is usually between 0 and 1, and is used to make the training a bit less aggressive.

The default weight multiplier is 0.4

See also

fann_set_cascade_weight_multiplier

This function appears in FANN >= 2.0.0.

fann_set_cascade_weight_multiplier

FANN_EXTERNAL void FANN_API fann_set_cascade_weight_multiplier(
   struct fann *ann,
   fann_type cascade_weight_multiplier
)

Sets the weight multiplier.

See also

fann_get_cascade_weight_multiplier

This function appears in FANN >= 2.0.0.

fann_get_cascade_candidate_limit

FANN_EXTERNAL fann_type FANN_API fann_get_cascade_candidate_limit(
   struct fann *ann
)

The candidate limit is a limit for how much the candidate neuron may be trained.  The limit is a limit on the proportion between the MSE and candidate score.

Set this to a lower value to avoid overfitting and to a higher if overfitting is not a problem.

The default candidate limit is 1000.0

See also

fann_set_cascade_candidate_limit

This function appears in FANN >= 2.0.0.

fann_set_cascade_candidate_limit

FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_limit(
   struct fann *ann,
   fann_type cascade_candidate_limit
)

Sets the candidate limit.

See also

fann_get_cascade_candidate_limit

This function appears in FANN >= 2.0.0.

fann_get_cascade_max_out_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_max_out_epochs(
   struct fann *ann
)

The maximum out epochs determines the maximum number of epochs the output connections may be trained after adding a new candidate neuron.

The default max out epochs is 150

See also

fann_set_cascade_max_out_epochs

This function appears in FANN >= 2.0.0.

fann_set_cascade_max_out_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_max_out_epochs(
   struct fann *ann,
   unsigned int cascade_max_out_epochs
)

Sets the maximum out epochs.

See also

fann_get_cascade_max_out_epochs

This function appears in FANN >= 2.0.0.

fann_get_cascade_min_out_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_min_out_epochs(
   struct fann *ann
)

The minimum out epochs determines the minimum number of epochs the output connections must be trained after adding a new candidate neuron.

The default min out epochs is 50

See also

fann_set_cascade_min_out_epochs

This function appears in FANN >= 2.2.0.

fann_set_cascade_min_out_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_min_out_epochs(
   struct fann *ann,
   unsigned int cascade_min_out_epochs
)

Sets the minimum out epochs.

See also

fann_get_cascade_min_out_epochs

This function appears in FANN >= 2.2.0.

fann_get_cascade_max_cand_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_max_cand_epochs(
   struct fann *ann
)

The maximum candidate epochs determines the maximum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.

The default max candidate epochs is 150

See also

fann_set_cascade_max_cand_epochs

This function appears in FANN >= 2.0.0.

fann_set_cascade_max_cand_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_max_cand_epochs(
   struct fann *ann,
   unsigned int cascade_max_cand_epochs
)

Sets the max candidate epochs.

See also

fann_get_cascade_max_cand_epochs

This function appears in FANN >= 2.0.0.

fann_get_cascade_min_cand_epochs

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_min_cand_epochs(
   struct fann *ann
)

The minimum candidate epochs determines the minimum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.

The default min candidate epochs is 50

See also

fann_set_cascade_min_cand_epochs

This function appears in FANN >= 2.2.0.

fann_set_cascade_min_cand_epochs

FANN_EXTERNAL void FANN_API fann_set_cascade_min_cand_epochs(
   struct fann *ann,
   unsigned int cascade_min_cand_epochs
)

Sets the min candidate epochs.

See also

fann_get_cascade_min_cand_epochs

This function appears in FANN >= 2.2.0.

fann_get_cascade_num_candidates

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_num_candidates(
   struct fann *ann
)

The number of candidates used during training (calculated by multiplying fann_get_cascade_activation_functions_count, fann_get_cascade_activation_steepnesses_count and fann_get_cascade_num_candidate_groups).

The actual candidates is defined by the fann_get_cascade_activation_functions and fann_get_cascade_activation_steepnesses arrays.  These arrays define the activation functions and activation steepnesses used for the candidate neurons.  If there are 2 activation functions in the activation function array and 3 steepnesses in the steepness array, then there will be 2x3=6 different candidates which will be trained.  These 6 different candidates can be copied into several candidate groups, where the only difference between these groups is the initial weights.  If the number of groups is set to 2, then the number of candidate neurons will be 2x3x2=12.  The number of candidate groups is defined by fann_set_cascade_num_candidate_groups.

The default number of candidates is 6x4x2 = 48

See also

fann_get_cascade_activation_functions, fann_get_cascade_activation_functions_count, fann_get_cascade_activation_steepnesses, fann_get_cascade_activation_steepnesses_count, fann_get_cascade_num_candidate_groups

This function appears in FANN >= 2.0.0.

fann_get_cascade_activation_functions_count

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_activation_functions_count(
   struct fann *ann
)

The number of activation functions in the fann_get_cascade_activation_functions array.

The default number of activation functions is 10.

See also

fann_get_cascade_activation_functions, fann_set_cascade_activation_functions

This function appears in FANN >= 2.0.0.

fann_get_cascade_activation_functions

FANN_EXTERNAL enum fann_activationfunc_enum * FANN_API fann_get_cascade_activation_functions(
   struct fann *ann
)

The cascade activation functions array is an array of the different activation functions used by the candidates.

See fann_get_cascade_num_candidates for a description of which candidate neurons will be generated by this array.

The default activation functions are {FANN_SIGMOID, FANN_SIGMOID_SYMMETRIC, FANN_GAUSSIAN, FANN_GAUSSIAN_SYMMETRIC, FANN_ELLIOT, FANN_ELLIOT_SYMMETRIC, FANN_SIN_SYMMETRIC, FANN_COS_SYMMETRIC, FANN_SIN, FANN_COS}

See also

fann_get_cascade_activation_functions_count, fann_set_cascade_activation_functions, fann_activationfunc_enum

This function appears in FANN >= 2.0.0.

fann_set_cascade_activation_functions

FANN_EXTERNAL void FANN_API fann_set_cascade_activation_functions(
   struct fann *ann,
   enum fann_activationfunc_enum *cascade_activation_functions,
   unsigned int cascade_activation_functions_count
)

Sets the array of cascade candidate activation functions.  The array must be just as long as defined by the count.

See fann_get_cascade_num_candidates for a description of which candidate neurons will be generated by this array.

See also

fann_get_cascade_activation_steepnesses_count, fann_get_cascade_activation_steepnesses

This function appears in FANN >= 2.0.0.

fann_get_cascade_activation_steepnesses_count

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_activation_steepnesses_count(
   struct fann *ann
)

The number of activation steepnesses in the fann_get_cascade_activation_functions array.

The default number of activation steepnesses is 4.

See also

fann_get_cascade_activation_steepnesses, fann_set_cascade_activation_functions

This function appears in FANN >= 2.0.0.

fann_get_cascade_activation_steepnesses

FANN_EXTERNAL fann_type * FANN_API fann_get_cascade_activation_steepnesses(
   struct fann *ann
)

The cascade activation steepnesses array is an array of the different activation functions used by the candidates.

See fann_get_cascade_num_candidates for a description of which candidate neurons will be generated by this array.

The default activation steepnesses is {0.25, 0.50, 0.75, 1.00}

See also

fann_set_cascade_activation_steepnesses, fann_get_cascade_activation_steepnesses_count

This function appears in FANN >= 2.0.0.

fann_set_cascade_activation_steepnesses

FANN_EXTERNAL void FANN_API fann_set_cascade_activation_steepnesses(
   struct fann *ann,
   fann_type *cascade_activation_steepnesses,
   unsigned int cascade_activation_steepnesses_count
)

Sets the array of cascade candidate activation steepnesses.  The array must be just as long as defined by the count.

See fann_get_cascade_num_candidates for a description of which candidate neurons will be generated by this array.

See also

fann_get_cascade_activation_steepnesses, fann_get_cascade_activation_steepnesses_count

This function appears in FANN >= 2.0.0.

fann_get_cascade_num_candidate_groups

FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_num_candidate_groups(
   struct fann *ann
)

The number of candidate groups is the number of groups of identical candidates which will be used during training.

This number can be used to have more candidates without having to define new parameters for the candidates.

See fann_get_cascade_num_candidates for a description of which candidate neurons will be generated by this parameter.

The default number of candidate groups is 2

See also

fann_set_cascade_num_candidate_groups

This function appears in FANN >= 2.0.0.

fann_set_cascade_num_candidate_groups

FANN_EXTERNAL void FANN_API fann_set_cascade_num_candidate_groups(
   struct fann *ann,
   unsigned int cascade_num_candidate_groups
)

Sets the number of candidate groups.

See also

fann_get_cascade_num_candidate_groups

This function appears in FANN >= 2.0.0.

FANN_EXTERNAL void FANN_API fann_cascadetrain_on_data(
   struct fann *ann,
   struct fann_train_data *data,
   unsigned int max_neurons,
   unsigned int neurons_between_reports,
   float desired_error
)
Trains on an entire dataset, for a period of time using the Cascade2 training algorithm.
FANN_EXTERNAL void FANN_API fann_cascadetrain_on_file(
   struct fann *ann,
   const char *filename,
   unsigned int max_neurons,
   unsigned int neurons_between_reports,
   float desired_error
)
Does the same as fann_cascadetrain_on_data, but reads the training data directly from a file.
FANN_EXTERNAL float FANN_API fann_get_cascade_output_change_fraction(
   struct fann *ann
)
The cascade output change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_output_stagnation_epochs during training of the output connections, in order for the training not to stagnate.
FANN_EXTERNAL float FANN_API fann_get_MSE(struct fann *ann)
Reads the mean square error from the network.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_output_stagnation_epochs(
   struct fann *ann
)
The number of cascade output stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_output_change_fraction.
FANN_EXTERNAL void FANN_API fann_set_cascade_output_change_fraction(
   struct fann *ann,
   float cascade_output_change_fraction
)
Sets the cascade output change fraction.
FANN_EXTERNAL void FANN_API fann_set_cascade_output_stagnation_epochs(
   struct fann *ann,
   unsigned int cascade_output_stagnation_epochs
)
Sets the number of cascade output stagnation epochs.
FANN_EXTERNAL float FANN_API fann_get_cascade_candidate_change_fraction(
   struct fann *ann
)
The cascade candidate change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE value should change within fann_get_cascade_candidate_stagnation_epochs during training of the candidate neurons, in order for the training not to stagnate.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_candidate_stagnation_epochs(
   struct fann *ann
)
The number of cascade candidate stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by a fraction of fann_get_cascade_candidate_change_fraction.
FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_change_fraction(
   struct fann *ann,
   float cascade_candidate_change_fraction
)
Sets the cascade candidate change fraction.
FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_stagnation_epochs(
   struct fann *ann,
   unsigned int cascade_candidate_stagnation_epochs
)
Sets the number of cascade candidate stagnation epochs.
FANN_EXTERNAL fann_type FANN_API fann_get_cascade_weight_multiplier(
   struct fann *ann
)
The weight multiplier is a parameter which is used to multiply the weights from the candidate neuron before adding the neuron to the neural network.
FANN_EXTERNAL void FANN_API fann_set_cascade_weight_multiplier(
   struct fann *ann,
   fann_type cascade_weight_multiplier
)
Sets the weight multiplier.
FANN_EXTERNAL fann_type FANN_API fann_get_cascade_candidate_limit(
   struct fann *ann
)
The candidate limit is a limit for how much the candidate neuron may be trained.
FANN_EXTERNAL void FANN_API fann_set_cascade_candidate_limit(
   struct fann *ann,
   fann_type cascade_candidate_limit
)
Sets the candidate limit.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_max_out_epochs(
   struct fann *ann
)
The maximum out epochs determines the maximum number of epochs the output connections may be trained after adding a new candidate neuron.
FANN_EXTERNAL void FANN_API fann_set_cascade_max_out_epochs(
   struct fann *ann,
   unsigned int cascade_max_out_epochs
)
Sets the maximum out epochs.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_min_out_epochs(
   struct fann *ann
)
The minimum out epochs determines the minimum number of epochs the output connections must be trained after adding a new candidate neuron.
FANN_EXTERNAL void FANN_API fann_set_cascade_min_out_epochs(
   struct fann *ann,
   unsigned int cascade_min_out_epochs
)
Sets the minimum out epochs.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_max_cand_epochs(
   struct fann *ann
)
The maximum candidate epochs determines the maximum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.
FANN_EXTERNAL void FANN_API fann_set_cascade_max_cand_epochs(
   struct fann *ann,
   unsigned int cascade_max_cand_epochs
)
Sets the max candidate epochs.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_min_cand_epochs(
   struct fann *ann
)
The minimum candidate epochs determines the minimum number of epochs the input connections to the candidates may be trained before adding a new candidate neuron.
FANN_EXTERNAL void FANN_API fann_set_cascade_min_cand_epochs(
   struct fann *ann,
   unsigned int cascade_min_cand_epochs
)
Sets the min candidate epochs.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_num_candidates(
   struct fann *ann
)
The number of candidates used during training (calculated by multiplying fann_get_cascade_activation_functions_count, fann_get_cascade_activation_steepnesses_count and fann_get_cascade_num_candidate_groups).
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_activation_functions_count(
   struct fann *ann
)
The number of activation functions in the fann_get_cascade_activation_functions array.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_activation_steepnesses_count(
   struct fann *ann
)
The number of activation steepnesses in the fann_get_cascade_activation_functions array.
FANN_EXTERNAL unsigned int FANN_API fann_get_cascade_num_candidate_groups(
   struct fann *ann
)
The number of candidate groups is the number of groups of identical candidates which will be used during training.
FANN_EXTERNAL enum fann_activationfunc_enum * FANN_API fann_get_cascade_activation_functions(
   struct fann *ann
)
The cascade activation functions array is an array of the different activation functions used by the candidates.
FANN_EXTERNAL void FANN_API fann_set_cascade_activation_functions(
   struct fann *ann,
   enum fann_activationfunc_enum *cascade_activation_functions,
   unsigned int cascade_activation_functions_count
)
Sets the array of cascade candidate activation functions.
FANN_EXTERNAL fann_type * FANN_API fann_get_cascade_activation_steepnesses(
   struct fann *ann
)
The cascade activation steepnesses array is an array of the different activation functions used by the candidates.
FANN_EXTERNAL void FANN_API fann_set_cascade_activation_steepnesses(
   struct fann *ann,
   fann_type *cascade_activation_steepnesses,
   unsigned int cascade_activation_steepnesses_count
)
Sets the array of cascade candidate activation steepnesses.
FANN_EXTERNAL void FANN_API fann_set_cascade_num_candidate_groups(
   struct fann *ann,
   unsigned int cascade_num_candidate_groups
)
Sets the number of candidate groups.
FANN_EXTERNAL struct fann *FANN_API fann_create_shortcut(
   unsigned int num_layers,
    ...
)
Creates a standard backpropagation neural network, which is fully connected and which also has shortcut connections.
FANN_EXTERNAL void FANN_API fann_set_training_algorithm(
   struct fann *ann,
   enum fann_train_enum training_algorithm
)
Set the training algorithm.
FANN_EXTERNAL unsigned int FANN_API fann_get_bit_fail(struct fann *ann)
The number of fail bits; means the number of output neurons which differ more than the bit fail limit (see fann_get_bit_fail_limit, fann_set_bit_fail_limit).
FANN_EXTERNAL void FANN_API fann_set_train_stop_function(
   struct fann *ann,
   enum fann_stopfunc_enum train_stop_function
)
Set the stop function used during training.
FANN_EXTERNAL void FANN_API fann_set_callback(struct fann *ann,
fann_callback_type callback)
Sets the callback function for use during training.
FANN_EXTERNAL void FANN_API fann_train_on_data(
   struct fann *ann,
   struct fann_train_data *data,
   unsigned int max_epochs,
   unsigned int epochs_between_reports,
   float desired_error
)
Trains on an entire dataset, for a period of time.
The activation functions used for the neurons during training.
Close