LSTM Can Solve Hard Long Time Lag Problems
Abstract
Standard recurrent nets cannot deal with long minimal time lags between relevant signals. Several recent NIPS papers propose alter(cid:173) native 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.
Cite
Text
Hochreiter and Schmidhuber. "LSTM Can Solve Hard Long Time Lag Problems." Neural Information Processing Systems, 1996.Markdown
[Hochreiter and Schmidhuber. "LSTM Can Solve Hard Long Time Lag Problems." Neural Information Processing Systems, 1996.](https://mlanthology.org/neurips/1996/hochreiter1996neurips-lstm/)BibTeX
@inproceedings{hochreiter1996neurips-lstm,
title = {{LSTM Can Solve Hard Long Time Lag Problems}},
author = {Hochreiter, Sepp and Schmidhuber, Jürgen},
booktitle = {Neural Information Processing Systems},
year = {1996},
pages = {473-479},
url = {https://mlanthology.org/neurips/1996/hochreiter1996neurips-lstm/}
}