fann_train_epoch

(PECL fann >= 1.0.0)

fann_train_epoch — Train one epoch with a set of training data

説明

function fann_train_epoch(resource $ann, resource $data): float

Train one epoch with the training data stored in data. One epoch is where all of the training data is considered exactly once.

This function returns the MSE error as it is calculated either before or during the actual training. This is not the actual MSE after the training epoch, but since calculating this would require going through the entire training set once more, it is more than adequate to use this value during training.

The training algorithm used by this function is chosen by fann_set_training_algorithm() function.

パラメータ

ann: ニューラルネットワークリソース。
data: ニューラルネットワークトレーニングリソース。

戻り値

The MSE, or false on error.

参考

fann_train_on_data() - Trains on an entire dataset for a period of time
fann_test_data() - Test a set of training data and calculates the MSE for the training data
fann_get_MSE() - Reads the mean square error from the network
fann_set_training_algorithm() - Sets the training algorithm

関連キーワード:

training fann epoch train Train algorithm resource during actual entire ニューラルネットワークリソース Fann float stored considered exactly once calculated before after since calculating require