fann_init_weights

(PECL fann >= 1.0.0)

fann_init_weights — Initialize the weights using Widrow + Nguyen’s algorithm

説明

function fann_init_weights(resource $ann, resource $train_data): bool

Initialize the weights using Widrow + Nguyen’s algorithm.

This function behaves similarly to fann_randomize_weights(). It will use the algorithm developed by Derrick Nguyen and Bernard Widrow to set the weights in such a way as to speed up training. This technique is not always successful, and in some cases can be less efficient than a purely random initialization.

The algorithm requires access to the range of the input data (for example largest and smallest input), and therefore accepts a second argument, data, which is the training data that will be used to train the network.

パラメータ

ann: ニューラルネットワークリソース。
train_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

成功した場合に true、それ以外の場合に false を返します。

参考

fann_randomize_weights() - Give each connection a random weight between min_weight and max_weight
fann_read_train_from_file() - Reads a file that stores training data

関連キーワード:

weights fann algorithm Widrow Nguyen train Initialize using training init weight resource randomize random input ニューラルネットワークリソース length Fann behaves similarly developed Derrick Bernard