Paper
20 September 1996 Memory capacity of terminal attractor optical associative memory
Author Affiliations +
Abstract
The memory capacity of terminal attractor (TA) model associative memory is investigated based on the consistency between the stored pattern x$_i)(m) and the obtained equilibrium state xi in statistical thermodynamics. By the computer simulations, we give intuitive estimates of the memory capacity of the TA model associative memory. FOr the feasibility of the optical implementation of the TA associative memory, we impose some approximations to original TA associative memory without loosing the essence of the TA model. The memory capacity of such a modified TA model associative memory is also given by the numerical simulation. In this simulation, a 10 X 10 neuron network model is used and Hamming distances among inputs and the stored patterns are chosen to be equal to 5 or more both in the original and modified TA models. The results indicate that the absolute memory capacity of the TA model is greater than 0.35N, which contrasts with the relative capacity of 0.15N or the theoretical absolute capacity of N/(41nN) for the conventional associative memory.
© (1996) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Xin Lin and Junji Ohtsubo "Memory capacity of terminal attractor optical associative memory", Proc. SPIE 2890, Optical Recording, Storage, and Retrieval Systems, (20 September 1996); https://doi.org/10.1117/12.251970
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Content addressable memory

Neural networks

Neurons

Numerical simulations

Computer simulations

Mathematical modeling

Thermodynamics

RELATED CONTENT


Back to Top