Journal
NEURAL NETWORKS
Volume 16, Issue 2, Pages 241-250Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/S0893-6080(02)00219-8
Keywords
long short-term memory; recurrent neural networks; decoupled extended Kalman filter; online prediction; context sensitive language inference
Ask authors/readers for more resources
The long short-term memory (LSTM) network trained by gradient descent solves difficult problems which traditional recurrent neural networks in general cannot. We have recently observed that the decoupled extended Kalman filter training algorithm allows for even better performance, reducing significantly the number of training steps when compared to the original gradient descent training algorithm. In this paper we present a set of experiments which are unsolvable by classical recurrent networks but which are solved elegantly and robustly and quickly by LSTM combined with Kalman filters. (C) 2003 Elsevier Science Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available