(PECL fann >= 1.0.0) Saves the entire network to a configuration file bool fann_save ( resource $ann, string $configuration_file ) Saves the entire network to a configuration file. The configuration file contains all information about the neural network and enables fann_create_from_file() to create an exact copy of the neural network and all of the parameters associated with the neural network. These three parameters

(PECL fann >= 1.0.0) Save the training structure to a file bool fann_save_train ( resource $data, string $file_name ) Save the training data to a file, with the format as specified in fann_read_train_from_file(). Parameters: data Neural network training data resource. file_name The file name of the file where training data is saved to.

(PECL fann >= 1.0.0) Will run input through the neural network array fann_run ( resource $ann, array $input ) Will run input through the neural network, returning an array of outputs, the number of which being equal to the number of neurons in the output layer. Parameters: ann Neural network resource. input Array of input values

(PECL fann >= 1.0.0) Resets the mean square error from the network bool fann_reset_MSE ( string $ann ) Resets the mean square error from the network. This function also resets the number of bits that fail. Parameters: ann Neural network resource. Returns: Returns TRUE on success, or FALSE otherwise.

(PECL fann >= 1.0.0) Resets the last error string void fann_reset_errstr ( resource $errdat ) Resets the last error string. Parameters: errdat Either neural network resource or neural network trainining data resource. Returns: No value is returned. See also: fa

(PECL fann >= 1.0.0) Resets the last error number void fann_reset_errno ( resource $errdat ) Resets the last error number. Parameters: errdat Either neural network resource or neural network trainining data resource. Returns: No value is returned. See also: fan

(PECL fann >= 1.0.0) Reads a file that stores training data resource fann_read_train_from_file ( string $filename ) Reads a file that stores training data. Parameters: filename The input file in the following format: num_train_data num_input num_output inputdata seperated by space outputdata seperated by space . . . inputdata seperated by space outputdata seperate

(PECL fann >= 1.0.0) Give each connection a random weight between min_weight and max_weight bool fann_randomize_weights ( resource $ann, float $min_weight, float $max_weight ) Give each connection a random weight between min_weight and max_weight From the beginning the weights are random between -0.1 and 0.1. Parameters: ann Neural network resource.

(PECL fann >= 1.0.0) Prints the error string void fann_print_error ( string $errdat ) Prints the error string. Parameters: errdat Either neural network resource or neural network trainining data resource. Returns: No value is returned. See also: fann_get_errstr

(PECL fann >= 1.0.0) Returns the number of outputs in each of the training patterns in the train data int fann_num_output_train_data ( resource $data ) Returns the number of outputs in each of the training patterns in the train data resource. Parameters: data Neural network training data resource. Returns: The number of outputs, or FALSE on erro