29 June 1989 Adaptive Dynamic Heteroassociative Neural Memories For Pattern Classification
Author Affiliations +
Proceedings Volume 1053, Optical Pattern Recognition; (1989); doi: 10.1117/12.951518
Event: OE/LASE '89, 1989, Los Angeles, CA, United States
Abstract
An adaptive dynamic artificial neural memory is proposed for pattern recognition applications. The proposed neural memory has a simple layered structure of neural processing units (neurons) with feedback which is ideal for parallel optical implementations. An adaptive version of our earlier-proposed high-performance neural memory recording algorithm (Ho-Kashyap recording algorithm) is utilized for the memory learning phase. This learning algorithm is computationaly inexpensive and leads to high-performance associative memory characteristics. The combination of this algorithm with a dynamic heteroassociative memory architecture gives rise to high associative memory capabilities which are suitable for adaptive and robust pattern classification applications. The state-space characteristics of dynamic heteroassociative memories (DAMs) utilizing various recording/synthesis algorithms are studied and the advantages of the proposed associative memory over the earlier proposed bidirectional associative memory (BAN) and generalized inverse-recorded heteroassociative memory are established and analyzed.
© (1989) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mohamad H. Hassoun, "Adaptive Dynamic Heteroassociative Neural Memories For Pattern Classification", Proc. SPIE 1053, Optical Pattern Recognition, (29 June 1989); doi: 10.1117/12.951518; https://doi.org/10.1117/12.951518
PROCEEDINGS
11 PAGES


SHARE
KEYWORDS
Detection and tracking algorithms

Content addressable memory

Neurons

Image classification

Bismuth

Pattern recognition

Optical pattern recognition

Back to Top