Are there any scientific papers or articles on use of bias vector regularization for training LSTM models ( I am using Keras: https://github.com/keras-team/keras/blob/master/keras/layers/recurrent.py#L2051 )?

I have used it for time series forecasting in stacked LSTM architecture and it improved evaluation results a lot, but I do not know why and how it works.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.