array ( 0 => 'index.php', 1 => 'PHP Manual', ), 'head' => array ( 0 => 'UTF-8', 1 => 'tr', ), 'this' => array ( 0 => 'function.fann-cascadetrain-on-data.php', 1 => 'fann_cascadetrain_on_data', 2 => 'Trains on an entire dataset, for a period of time using the Cascade2 training algorithm', ), 'up' => array ( 0 => 'ref.fann.php', 1 => 'Fann İşlevleri', ), 'prev' => array ( 0 => 'ref.fann.php', 1 => 'Fann İşlevleri', ), 'next' => array ( 0 => 'function.fann-cascadetrain-on-file.php', 1 => 'fann_cascadetrain_on_file', ), 'alternatives' => array ( ), 'source' => array ( 'lang' => 'en', 'path' => 'reference/fann/functions/fann-cascadetrain-on-data.xml', ), 'history' => array ( ), ); $setup["toc"] = $TOC; $setup["toc_deprecated"] = $TOC_DEPRECATED; $setup["parents"] = $PARENTS; manual_setup($setup); contributors($setup); ?>

fann_cascadetrain_on_data

(PECL fann >= 1.0.0)

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

Açıklama

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

The cascade output 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_output_stagnation_epochs() 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 training algorithm. This algorithm can be set to either FANN_TRAIN_RPROP or FANN_TRAIN_QUICKPROP by fann_set_training_algorithm(), and the parameters set for these training algorithms will also affect the cascade training.

Bağımsız Değişkenler

ann

Sinir ağı özkaynağı.

data

Sinir ağı eğitim verisi özkaynağı.

max_neurons

The maximum number of neurons to be added to neural network.

neurons_between_reports

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

desired_error

The desired fann_get_MSE() or fann_get_bit_fail(), depending on which stop function is chosen by fann_set_train_stop_function()

Dönen Değerler

Başarı durumunda true yoksa falsedöner.

Ayrıca Bakınız