Dynamic Autoassociative Neural Memory Performance VS. Capacity

Abbas M. Youssef; Mohamad H. Hassoun

doi:10.1117/12.951515

29 June 1989 Dynamic Autoassociative Neural Memory Performance VS. Capacity

Abbas M. Youssef, Mohamad H. Hassoun

Proceedings Volume 1053, Optical Pattern Recognition; (1989) https://doi.org/10.1117/12.951515
Event: OE/LASE '89, 1989, Los Angeles, CA, United States

Abstract

A new capacity measure is proposed for the class of dynamic autoassociative neural memories (ANMs). The proposed associative memory capacity measure is based on the memory's performance vs. the number of stored memory vectors, where performance is defined in terms of the memory's error-correcting ability and its fundamental memories' attraction volumes. This new method of measuring ANM capacity is very effective when ANMs are used in pattern recognition and error-tolerant content-addressable memories. The proposed capacity/performance measure has been tested for several ANMs having the same dynamic Hopfield memory-like architecture, each employing a different recording technique. Correlation, generalized inverse (orthogonal), and Ho-Kashyap memory recordings have been investigated. Monte Carlo analysis has been performed on ANMs recorded with randomly generated patterns, in order to determine and compare performance characteristics and dynamics.

Citation Download Citation

Abbas M. Youssef and Mohamad H. Hassoun "Dynamic Autoassociative Neural Memory Performance VS. Capacity", Proc. SPIE 1053, Optical Pattern Recognition, (29 June 1989); https://doi.org/10.1117/12.951515

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available