Learning long-term dependencies with gradient descent is difficult

Abstract

Recurrent neural networks can be used to map input sequences to output sequences, such as for recognition, production or prediction problems. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input/output sequences span long intervals. We show why gradient based learning algorithms face an increasingly difficult problem as the duration of the dependencies to be captured increases. These results expose a trade-off between efficient learning by gradient descent and latching on information for long periods. Based on an understanding of this problem, alternatives to standard gradient descent are considered.

Cite this paper

Related papers

1. Long Short-Term Memory1997
2. Gradient-based learning applied to document recognition1998
3. Particle swarm optimization2002
4. LIBSVM2011
5. Greedy function approximation: A gradient boosting machine.2001