fann_sys::fann_cascadetrain_on_data

pub unsafe extern fn fann_cascadetrain_on_data(ann: *mut fann, data: *const fann_train_data, max_neurons: c_uint, neurons_between_reports: c_uint, desired_error: c_float)

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:

let 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 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

• ann - The neural network
• data - The data that should be used during training
• max_neuron - The maximum number of neurons to be added to the ANN
• neurons_between_reports - The number of neurons between printing a status report to stdout. A value of zero means no reports should be printed.
• desired_error - The 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

This function appears in FANN >= 2.0.0.