Title: 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 trai...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.Read More
Publication Year: 1994
Publication Date: 1994-03-01
Language: en
Type: article
Indexed In: ['crossref', 'pubmed']
Access and Citation
Cited By Count: 7520
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot