Paper

Credit Assignment through Time: Alternatives to Backpropagation

Learning to recognize or predict sequences using long-term context has many applications. However, practical and theoretical problems are found in training recurrent neural networks to perform tasks in which input/output dependencies span long intervals. Starting from a mathematical analysis of the problem, we consider and compare alternative algorithms and architectures on tasks for which the span of the input/output dependencies can be controlled. Results on the new algorithms show performance qualitatively superior to that obtained with backpropagation. 1 Introduction Recurrent neural networks have been considered to learn to map input sequences to output sequences. Machines that could efficiently learn such tasks would be useful for many applications involving sequence prediction, recognition or production. However, practical difficulties have been reported in training recurrent neural networks to perform tasks in which the temporal contingencies present in the input /output seque...

ftp://ftp-dsi.ing.unifi.it/pub/tech-reports/alternatives.nips93.ps.ZPublished 1993-11-29Paper link

Authors: Yoshua Bengio · Paolo Frasconi

Topics

Relevant entities

People

Related coverage

Linked coverage will appear here.

Related events

Linked events will appear here.

Related discussions

Related discussion nodes will appear here.