fann_get_bit_fail(3) [php man page]

FANN_GET_BIT_FAIL(3)							 1						      FANN_GET_BIT_FAIL(3)

fann_get_bit_fail - The number of fail bits

SYNOPSIS

       int fann_get_bit_fail (resource	$ann)

DESCRIPTION

	The  number  of  fail  bits; means the number of output neurons which differ more than the bit fail limit (see fann_get_bit_fail_limit(3),
       fann_set_bit_fail_limit(3)). The bits are counted in all of the training data, so this number can be higher than  the  number  of  training
       data.

	This  value  is reset by fann_reset_MSE(3) and updated by all the same functions which also updates the MSE value (e.g. fann_test_data(3),
       fann_train_epoch(3))

PARAMETERS

	      o $ann
		-Neural network resource.

RETURN VALUES

	The number of bits fail, or FALSE on error.

SEE ALSO

       fann_get_MSE(3), fann_reset_MSE(3), fann_test_data(3), fann_train_epoch(3), fann_get_bit_fail_limit(3), fann_set_bit_fail_limit(3).

PHP Documentation Group 												      FANN_GET_BIT_FAIL(3)

FANN_CASCADETRAIN_ON_DATA(3)						 1					      FANN_CASCADETRAIN_ON_DATA(3)

fann_cascadetrain_on_data - Trains on an entire dataset, for a period of time using the Cascade2 training algorithm

SYNOPSIS

       bool fann_cascadetrain_on_data (resource  $ann, resource  $data, int  $max_neurons, int	$neurons_between_reports, float  $desired_error)

DESCRIPTION

	The  cascade  output  change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE(3) value should change
       within fann_get_cascade_output_stagnation_epochs(3) during training of the output connections, in order for the training not  to  stagnate.
       If the training stagnates, the training of the output connections will be ended and new candidates will be prepared.

	This  training uses the parameters set using the fann_set_cascade_..., but it also uses another training algorithm as it's internal train-
       ing algorithm. This algorithm can be set to either FANN_TRAIN_RPROP or  FANN_TRAIN_QUICKPROP  by  fann_set_training_algorithm(3),  and  the
       parameters set for these training algorithms will also affect the cascade training.

PARAMETERS

	      o $ann
		-Neural network resource.

	      o $data
		-Neural network training data resource.

	      o $max_neurons
		- The maximum number of neurons to be added to neural network.

	      o $neurons_between_reports
		- The number of neurons between printing a status report. A value of zero means no reports should be printed.

	      o $desired_error
		-  The	desired  fann_get_MSE(3)  or fann_get_bit_fail(3), depending on which stop function is chosen by fann_set_train_stop_func-
		tion(3)

RETURN VALUES

       Returns TRUE on success, or FALSE otherwise.

SEE ALSO

       fann_train_on_data(3), fann_cascadetrain_on_file(3).

PHP Documentation Group 											      FANN_CASCADETRAIN_ON_DATA(3)