fann_get_cascade_output_stagnation_epochs(3) [php man page]

FANN_GET_CASCADE_OUTPUT_STAGNATION_EPOCHS(3)				 1			      FANN_GET_CASCADE_OUTPUT_STAGNATION_EPOCHS(3)

fann_get_cascade_output_stagnation_epochs - Returns the number of cascade output stagnation epochs

SYNOPSIS

       int fann_get_cascade_output_stagnation_epochs (resource	$ann)

DESCRIPTION

	The number of cascade output stagnation epochs determines the number of epochs training is allowed to continue without changing the MSE by
       a fraction of fann_get_cascade_output_change_fraction(3).

	See more info about this parameter in fann_get_cascade_output_change_fraction(3).

	The default number of cascade output stagnation epochs is 12.

PARAMETERS

	      o $ann
		-Neural network resource.

RETURN VALUES

	The number of cascade output stagnation epochs, or FALSE on error.

SEE ALSO

       fann_set_cascade_output_stagnation_epochs(3), fann_get_cascade_output_change_fraction(3).

PHP Documentation Group 									      FANN_GET_CASCADE_OUTPUT_STAGNATION_EPOCHS(3)

FANN_GET_CASCADE_CANDIDATE_CHANGE_FRACTION(3)				 1			     FANN_GET_CASCADE_CANDIDATE_CHANGE_FRACTION(3)

fann_get_cascade_candidate_change_fraction - Returns the cascade candidate change fraction

SYNOPSIS

       float fann_get_cascade_candidate_change_fraction (resource  $ann)

DESCRIPTION

	The cascade candidate 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_candidate_stagnation_epochs(3) during training of the candidate neurons, in order for the training not to stagnate.
       If the training stagnates, the training of the candidate neurons will be ended and the best candidate will be selected.

	It  means  that if the MSE does not change by a fraction of fann_get_cascade_candidate_change_fraction(3) during a period of fann_get_cas-
       cade_candidate_stagnation_epochs(3), the training of the candidate neurons is stopped because the training has stagnated.

	If the cascade candidate change fraction is low, the candidate neurons will be trained more and if the	fraction  is  high  they  will	be
       trained less.

	The default cascade candidate change fraction is 0.01, which is equalent to a 1% change in MSE.

PARAMETERS

	      o $ann
		-Neural network resource.

RETURN VALUES

	The cascade candidate change fraction, or FALSE on error.

SEE ALSO

       fann_set_cascade_candidate_change_fraction(3), fann_get_MSE(3), fann_get_cascade_candidate_stagnation_epochs(3).

PHP Documentation Group 									     FANN_GET_CASCADE_CANDIDATE_CHANGE_FRACTION(3)