fann_train_on_data
(PECL fann >= 1.0.0)
fann_train_on_data — Trains on an entire dataset for a period of time
Description
fann_train_on_data(
resource
resource
int
int
float
): bool
resource
$ann,resource
$data,int
$max_epochs,int
$epochs_between_reports,float
$desired_error): bool
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
annNeural network resource.
dataNeural network training data resource.
max_epochsThe maximum number of epochs the training should continue
epochs_between_reportsThe number of epochs between calling a callback function. A value of zero means that user function is not called.
desired_errorThe desired fann_get_MSE() or fann_get_bit_fail(), depending on the stop function chosen by fann_set_train_stop_function()
See Also
- fann_train_on_file() - Trains on an entire dataset, which is read from file, for a period of time
- fann_train_epoch() - Train one epoch with a set of training data
- fann_get_bit_fail() - The number of fail bits
- fann_get_MSE() - Reads the mean square error from the network
- fann_set_train_stop_function() - Sets the stop function used during training
- fann_set_training_algorithm() - Sets the training algorithm
- fann_set_callback() - Sets the callback function for use during training
↑ and ↓ to navigate • Enter to select • Esc to close • / to open