(PECL fann >= 1.0.0) Get the number of bias in each layer in the network array fann_get_bias_array ( resource $ann ) Get the number of bias in each layer in the network. Parameters: ann Neural network resource. Returns: An array of numbers of bias in each layer

(PECL fann >= 1.0.0) Returns the activation steepness for supplied neuron and layer number float fann_get_activation_steepness ( resource $ann, int $layer, int $neuron ) Get the activation steepness for neuron number neuron in layer number layer, counting the input layer as layer 0. It is not possible to get activation steepness for the neurons in the input layer. The steepness of an activation function says something

(PECL fann >= 1.0.0) Returns the activation function int fann_get_activation_function ( resource $ann, int $layer, int $neuron ) Get the activation function for neuron number neuron in layer number layer, counting the input layer as layer 0. It is not possible to get activation functions for the neurons in the input layer. The return value is one of the activation functions constants. Parameters:

(PECL fann >= 1.0.0) Returns an exact copy of a fann train data resource fann_duplicate_train_data ( resource $data ) Returns an exact copy of a fann train data resource. Parameters: data Neural network training data resource. Returns: Returns a train data resource on success, or FALSE on error.

(PECL fann >= 1.0.0) Destroys the entire network and properly freeing all the associated memory bool fann_destroy ( resource $ann ) Destroys the entire network and properly freeing all the associated memory. Parameters: ann Neural network resource. Returns: Returns TRUE on success, or FALSE otherwise.

(PECL fann >= 1.0.0) Destructs the training data bool fann_destroy_train ( resource $train_data ) Destructs the training data Parameters: train_data Neural network training data resource. Returns: Returns TRUE on success, or FALSE otherwise.

(PECL fann >= 1.0.0) Descale input and output data based on previously calculated parameters bool fann_descale_train ( resource $ann, resource $train_data ) Descale input and output data based on previously calculated parameters. Parameters: ann Neural network resource. train_data Neural network training data resource.

(PECL fann >= 1.0.0) Scale data in output vector after get it from ann based on previously calculated parameters bool fann_descale_output ( resource $ann, array $output_vector ) Scale data in output vector after get it from ann based on previously calculated parameters. Parameters: ann Neural network resource. output_vector Output vect

(PECL fann >= 1.0.0) Scale data in input vector after get it from ann based on previously calculated parameters bool fann_descale_input ( resource $ann, array $input_vector ) Scale data in input vector after get it from ann based on previously calculated parameters. Parameters: ann Neural network resource. input_vector Input vector tha

(PECL fann >= 1.0.0) Creates an empty training data struct resource fann_create_train ( int $num_data, int $num_input, int $num_output ) Creates an empty training data struct. Parameters: num_data The number of training data num_input The number of inputs per training data num_output The number of