Share Email Print

Proceedings Paper

A High-Performance Associative Neural Memory (ANM) For Pattern Recognition
Author(s): M. H. Hassoun
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

A high-performance, high-capacity associative neural memory (ANM) architecture is proposed. The proposed ANM architecture is based on a cascade of two-levels of fully interconnected layers of binary neurons. Feedback is used to connect the output of the second neural layer to the input of the first layer in order to increase network convergence rate and retrieval accuracy. The proposed ANM training (recording) is accomplished by the use of a very efficient newly-developed recording technique. The combination of the above powerful recording technique and the two-level with feedback ANM architecture gives rise to a high-performance network for pattern recognition applications. The proposed architecture allows for simultaneous autoassociative and heteroassociative memory operation which implies both pattern reconstruction and pattern classification capabilities. Finally, the highly parallel and distributed architecture of the above ANM can greatly benefit from the intrinsic parallelism and high interconnection capacity offered by optical systems.

Paper Details

Date Published: 12 October 1988
PDF: 9 pages
Proc. SPIE 0956, Piece Recognition and Image Processing, (12 October 1988); doi: 10.1117/12.947693
Show Author Affiliations
M. H. Hassoun, Wayne State University (United States)

Published in SPIE Proceedings Vol. 0956:
Piece Recognition and Image Processing
Wayne Wiitanen, Editor(s)

© SPIE. Terms of Use
Back to Top