Snap-drift: real-time, performance-guided learning

Lee, SW, Palmer-Brown, D, Tepper, JA ORCID: https://orcid.org/0000-0001-7339-0132 and Roadknight, CM, 2003. Snap-drift: real-time, performance-guided learning. In: Proceedings of the International Joint Conference on Neural Networks. Piscataway, NJ, USA: IEEE, pp. 1412-1416. ISBN 0780378989

Full text not available from this repository.

Abstract

A novel approach for real-time learning and mapping of patterns using an external performance indicator is described. The learning makes use of the 'snap-drift' algorithm based on the concept of fast, convergent, minimalist learning (snap) when the overall network performance has been poor and slower, cautious learning (drift towards user request input patterns) when the performance has been good, in a non-stationary environment where new patterns are being introduces over time. Snap is based on adaptive resonance; and drift is based on learning vector quantization (LVQ). The two are combined in a semi-supervised system that shifts its learning style whenever it receives a change in performance feedback. The learning is capable of rapidly relearning and reestablishing, according to changes in feedback or patterns. We have used this algorithm in the design of a modular neural network system, known as performance-guided adaptive resonance theory (P-ART). Simulation results show that it discovers alternative sol

Item Type:	Chapter in book
Creators:	Lee, S.W., Palmer-Brown, D., Tepper, J.A. and Roadknight, C.M.
Publisher:	IEEE
Place of Publication:	Piscataway, NJ, USA
Date:	2003
Volume:	2
ISBN:	0780378989
Divisions:	Schools > School of Science and Technology
Record created by:	EPrints Services
Date Added:	09 Oct 2015 11:07
Last Modified:	04 Feb 2022 12:36
URI:	https://irep.ntu.ac.uk/id/eprint/23194

Actions (login required)

Edit View

Statistics

Views

Downloads