LSTM can solve hard long time lag problems

Sepp Hochreiter, Jürgen Schmidhuber

Research output: Chapter in Book/Report/Conference proceedingConference contribution

713 Scopus citations


Standard recurrent nets cannot deal with long minimal time lags between relevant signals. Several recent NIPS papers propose alternative methods. We first show: problems used to promote various previous algorithms can be solved more quickly by random weight guessing than by the proposed algorithms. We then use LSTM, our own recent algorithm, to solve a hard problem that can neither be quickly solved by random search nor by any other recurrent net algorithm we are aware of.
Original languageEnglish (US)
Title of host publicationAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
Number of pages7
ISBN (Print)0262100657
StatePublished - Jan 1 1997
Externally publishedYes

Bibliographical note

Generated from Scopus record by KAUST IRTS on 2022-09-14


Dive into the research topics of 'LSTM can solve hard long time lag problems'. Together they form a unique fingerprint.

Cite this