single-jc.php

JACIII Vol.2 No.6 pp. 221-227
doi: 10.20965/jaciii.1998.p0221
(1998)

Paper:

Local Learning Algorithms for Sequential Tasks in Neural Networks

Anthony Robins* and Marcus Frean**

*Computer Science, The University of Otago PO Box 56, Dunedin, New Zealand

**Electrical and Computer Engineering, University of Queensland Brisbane 4072, Australia

Received:
May 10, 1998
Accepted:
August 29, 1998
Published:
December 20, 1998
Keywords:
Local learning, Pseudorehearsal, Catastrophic forgetting, Generalization
Abstract

In this paper, we explore the concept of sequential learning and the efficacy of global and local neural network learning algorithms on a sequential learning task. Pseudorehearsal, a method developed by Robins19) to solve the catastrophic forgetting problem which arises from the excessive plasticity of neural networks, is significantly more effective than other local learning algorithms for the sequential task. We further consider the concept of local learning and suggest that pseudorehearsal is so effective because it works directly at the level of the learned function, and not indirectly on the representation of the function within the network. We also briefly explore the effect of local learning on generalization within the task.

Cite this article as:
Anthony Robins and Marcus Frean, “Local Learning Algorithms for Sequential Tasks in Neural Networks,” J. Adv. Comput. Intell. Intell. Inform., Vol.2, No.6, pp. 221-227, 1998.
Data files:

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on Sep. 14, 2021