(PECL fann >= 1.0.0) Creates the training data struct from a user supplied function resource fann_create_train_from_callback ( int $num_data, int $num_input, int $num_output, callable $user_function ) Creates the training data struct from a user supplied function. As the training data are numerable (data 1, data 2...), the user must write a function that receives the number of the training data set (input, output) and ret

(PECL fann >= 1.0.0) Creates a standard fully connected backpropagation neural network resource fann_create_standard ( int $num_layers, int $num_neurons1, int $num_neurons2 [, int $... ] ) Creates a standard fully connected backpropagation neural network. There will be a bias neuron in each layer (except the output layer), and this bias neuron will be connected to all neurons in the next layer. When running the network,

(PECL fann >= 1.0.0) Creates a standard fully connected backpropagation neural network using an array of layer sizes resource fann_create_standard_array ( int $num_layers, array $layers ) Creates a standard fully connected backpropagation neural network. There will be a bias neuron in each layer (except the output layer), and this bias neuron will be connected to all neurons in the next layer. When running the network,

(PECL fann >= 1.0.0) Creates a standard backpropagation neural network, which is not fully connected ReturnType fann_create_sparse ( float $connection_rate, int $num_layers, int $num_neurons1, int $num_neurons2 [, int $... ] ) Creates a standard backpropagation neural network, which is not fully connected. Parameters: connection_rate The connection rate controls how m

(PECL fann >= 1.0.0) Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes ReturnType fann_create_sparse_array ( float $connection_rate, int $num_layers, array $layers ) Creates a standard backpropagation neural network, which is not fully connected using an array of layer sizes. Parameters: connection_rate The c

(PECL fann >= 1.0.0) Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections reference fann_create_shortcut ( int $num_layers, int $num_neurons1, int $num_neurons2 [, int $... ] ) Creates a standard backpropagation neural network, which is not fully connected and which also has shortcut connections. Shortcut connections are connections that skip layers. A fully con

(PECL fann >= 1.0.0) Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections resource fann_create_shortcut_array ( int $num_layers, array $layers ) Creates a standard backpropagation neural network which is not fully connectected and has shortcut connections using an array of layers sizes. Parameters: num_layers Th

(PECL fann >= 1.0.0) Constructs a backpropagation neural network from a configuration file resource fann_create_from_file ( string $configuration_file ) Constructs a backpropagation neural network from a configuration file, which have been saved by fann_save(). Parameters: configuration_file The configuration file path. Returns: Returns a neur

(PECL fann >= 1.0.0) Creates a copy of a fann structure resource fann_copy ( resource $ann ) Creates a copy of a fann structure. Parameters: ann Neural network resource. Returns: Returns a copy of neural network resource on success, or FALSE on error See also:

(PECL fann >= 1.0.0) Clears scaling parameters bool fann_clear_scaling_params ( resource $ann ) Clears scaling parameters. Parameters: ann Neural network resource. Returns: Returns TRUE on success, or FALSE otherwise.