Regarding RNN training, We feed network a network -> point by point from the same time series (or image or smth else).

When we “switch from one time series to another”, what should be done or how network “will know” that the time series is different now?

What comes to my mind is to reset a hidden state or maybe to introduce some kind of symbol which "means" separation between inputs.

Are there any other or better options?


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.