(PECL fann >= 1.0.0) The connection constructor public FANNConnection::__construct ( int $from_neuron, int $to_neuron, float $weight ) Create new connection and initialize its params. After creating the connection, only weight can be changed. Parameters: from_neuron The postion number of starting neuron. to_neuron The postion number

(PECL fann >= 1.0.0) Train one iteration with a set of inputs, and a set of desired outputs bool fann_train ( resource $ann, array $input, array $desired_output ) Train one iteration with a set of inputs, and a set of desired outputs. This training is always incremental training, since only one pattern is presented. Parameters: ann Neural network resource.

(PECL fann >= 1.0.0) Trains on an entire dataset, which is read from file, for a period of time bool fann_train_on_file ( resource $ann, string $filename, int $max_epochs, int $epochs_between_reports, float $desired_error ) 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

(PECL fann >= 1.0.0) Trains on an entire dataset for a period of time bool fann_train_on_data ( resource $ann, resource $data, int $max_epochs, int $epochs_between_reports, float $desired_error ) Trains on an entire dataset 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. Parameters:

(PECL fann >= 1.0.0) Train one epoch with a set of training data float fann_train_epoch ( resource $ann, resource $data ) Train one epoch with the training data stored in data. One epoch is where all of the training data is considered exactly once. This function returns the MSE error as it is calculated either before or during the actual training. This is not the actual MSE after the training epoch, but since calculatin

(PECL fann >= 1.0.0) Test with a set of inputs, and a set of desired outputs bool fann_test ( resource $ann, array $input, array $desired_output ) Test with a set of inputs, and a set of desired outputs. This operation updates the mean square error, but does not change the network in any way. Parameters: ann Neural network resource. input

(PECL fann >= 1.0.0) Test a set of training data and calculates the MSE for the training data float fann_test_data ( resource $ann, resource $data ) Test a set of training data and calculates the MSE for the training data. This function updates the MSE and the bit fail values. Parameters: ann Neural network resource. data Neural netwo

(PECL fann >= 1.0.0) Returns an copy of a subset of the train data resource fann_subset_train_data ( resource $data, int $pos, int $length ) Returns an copy of a subset of the train data resource, starting at position pos and length elements forward. The fann_subset_train_data(train_data, 0, fann_length_train_data(train_data)) do the same as fann_duplicate_train_data() Parameters:

(PECL fann >= 1.0.0) Shuffles training data, randomizing the order bool fann_shuffle_train_data ( resource $train_data ) Shuffles training data, randomizing the order. This is recommended for incremental training, while it have no influence during batch training. Parameters: train_data Neural network training data resource. Returns: Returns TRUE

(PECL fann >= 1.0.0) Set a connection in the network bool fann_set_weight ( resource $ann, int $from_neuron, int $to_neuron, float $weight ) Set a connections in the network. Parameters: ann Neural network resource. from_neuron The neuron where the connection starts to_neuron The neuron where the con