According to Karpathy's blog "The Unreasonable Effectiveness of Recurrent Neural Networks", recurrent neural networks can map variable-length sequences to variable-length sequences, as shown by the one-to-many, many-to-one, and many-to-many diagrams.

How do RNN's do this mapping of possibly different-length sequences? It seems to me that there would need to be mechanisms that decide whether to accept input or to yield output on any given iteration. I don't see how RNN's have any such mechanisms.


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.