« fann_get_cascade_activation_steepnesses_count
fann_get_cascade_candidate_limit »

fann_get_cascade_candidate_change_fraction

(PECL fann >= 1.0.0)

fann_get_cascade_candidate_change_fraction — Returns the cascade candidate change fraction

説明

function fann_get_cascade_candidate_change_fraction(resource $ann): float

The cascade candidate change fraction is a number between 0 and 1 determining how large a fraction the fann_get_MSE() value should change within fann_get_cascade_candidate_stagnation_epochs() 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() during a period of fann_get_cascade_candidate_stagnation_epochs(), 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 equivalent to a 1% change in MSE.

パラメータ

ann

ニューラルネットワークリソース。

戻り値

The cascade candidate change fraction, or false on error.

参考

関連キーワード:
candidate   cascade   change   fraction   fann   training   stagnation   epochs   neurons   number   during   trained   activation   steepnesses   count   limit   Fann   resource   float   between   determining   large   within   order   stagnate
関連する関数・ページ:
function.fann-set-cascade-candidate-change-fraction   function.fann-get-cascade-output-change-fraction   function.fann-get-cascade-candidate-stagnation-epochs   function.fann-set-cascade-output-change-fraction   function.fann-get-cascade-output-stagnation-epochs   function.fann-set-cascade-candidate-limit