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

(PECL fann >= 1.0.0) Merges the train data resource fann_merge_train_data ( resource $data1, resource $data2 ) Merges the data from data1 and data2 into a new train data resource. Parameters: data1 Neural network training data resource. data2 Neural network training data resource. Returns: New merged train data

(PECL fann >= 1.0.0) Returns the number of training patterns in the train data int fann_length_train_data ( resource $data ) Returns the number of training patterns in the train data resource. Parameters: data Neural network training data resource. Returns: Number of elements in the train data resource, or FALSE on error.

(PECL fann >= 1.0.0) Initialize the weights using Widrow + Nguyen’s algorithm bool fann_init_weights ( resource $ann, resource $train_data ) Initialize the weights using Widrow + Nguyen’s algorithm. This function behaves similarly to fann_randomize_weights(). It will use the algorithm developed by Derrick Nguyen and Bernard Widrow to set the weights in such a way as to speed up training. This technique is not always suc

(PECL fann >= 1.0.0) Returns the training algorithm int fann_get_training_algorithm ( resource $ann ) Returns the training algorithm. This training algorithm is used by fann_train_on_data() and associated functions. Note that this algorithm is also used during fann_cascadetrain_on_data(), although only FANN_TRAIN_RPROP and FANN_TRAIN_QUICKPROP is allowed during cascade training. Parameters:

(PECL fann >= 1.0.0) Returns the stop function used during training int fann_get_train_stop_function ( resource $ann ) Returns the stop function used during training. The stop functions are described further in stop functions constants. The default stop function is FANN_STOPFUNC_MSE. Parameters: ann Neural network resource. Returns: The stop

(PECL fann >= 1.0.0) Returns the error function used during training int fann_get_train_error_function ( resource $ann ) Returns the error function used during training. The error functions are described further in error functions constants. The default error function is FANN_ERRORFUNC_TANH. Parameters: ann Neural network resource. Returns:

(PECL fann >= 1.0.0) Get the total number of neurons in the entire network int fann_get_total_neurons ( resource $ann ) Get the total number of neurons in the entire network. This number does also include the bias neurons, so a 2-4-2 network has 2+4+2 +2(bias) = 10 neurons. Parameters: ann Neural network resource. Returns: Total number of neuron

(PECL fann >= 1.0.0) Get the total number of connections in the entire network int fann_get_total_connections ( resource $ann ) Get the total number of connections in the entire network. Parameters: ann Neural network resource. Returns: Total number of connections in the entire network, or FALSE on error

(PECL fann >= 1.0.0) Returns the sarprop weight decay shift float fann_get_sarprop_weight_decay_shift ( resource $ann ) The sarprop weight decay shift. The default delta max is -6.644. Parameters: ann Neural network resource. Returns: The sarprop weight decay shift, or FALSE on error.