(PECL fann >= 1.0.0)
fann_train_on_file — Trains on an entire dataset, which is read from file, for a period of time
Trains on an entire dataset, which is read from file, for a period of time.
This training uses the training algorithm chosen by fann_set_training_algorithm() and the parameters set for these training algorithms.
resource da rede neural.
The file containing train data
The maximum number of epochs the training should continue
The number of epochs between calling a user function. A value of zero means that user function is not called.
TRUE no sucesso ou
FALSE em outros casos.