1. 程式人生 > >RNN(LSTM)網路可以使用那些正則化方法

RNN(LSTM)網路可以使用那些正則化方法

r2-regularization, weight decay

input dropout

mask dropout

weight dropout

activation regularization(AR)

temporal activation regularization(TAR)

adversarial dropout, fraternal dropout

Fraternal Dropout train two identical copies of an RNN (that share parameters) with different dropout masks while minimizing the difference between their (pre-softmax) predictions.