Long Short-Term Memory Article Swipe
YOU?
·
· 1997
·
· DOI: https://doi.org/10.1162/neco.1997.9.8.1735
· OA: W2064675550
Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, , mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis this problem, then address it introducing novel, efficient, gradient based method called short-term memory (LSTM). Truncating the where does not do harm, LSTM can learn bridge minimal lags in excess 1000 discrete-time steps enforcing constant flow through carousels within special units. Multiplicative gate units open and close access flow. is local space time; its computational complexity per step weight O. 1. Our experiments with artificial data involve local, distributed, real-valued, noisy pattern representations. In comparisons real-time learning, back propagation cascade correlation, Elman nets, neural sequence chunking, leads many more successful runs, learns much faster. also solves complex, long-time-lag tasks that have never been solved previous network algorithms.
