Paper
3 May 1988 Holographic Implementation Of A Discrete Hopfield Neural Network Model
H J White, W A Wright
Author Affiliations +
Proceedings Volume 0882, Neural Network Models for Optical Computing; (1988) https://doi.org/10.1117/12.944102
Event: 1988 Los Angeles Symposium: O-E/LASE '88, 1988, Los Angeles, CA, United States
Abstract
This paper investigates the feasibility of constructing a Hopfield neural network model using optical techniques. The use of thin holographic elements to form the weighted interconnections is discussed as well as the desirable response of 'nonlinear processing elements. This implementation is of a bipolar vector model and processes the negative numbers involved without using a subtraction stage. Our analysis suggests that although present day technology would limit the size of the network that could be implemented, the construction of an optical machine is now possible with a connectivity exceeding any curently available electronic machine.
© (1988) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
H J White and W A Wright "Holographic Implementation Of A Discrete Hopfield Neural Network Model", Proc. SPIE 0882, Neural Network Models for Optical Computing, (3 May 1988); https://doi.org/10.1117/12.944102
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Holography

Holograms

Neural networks

Diffraction

Systems modeling

Computer generated holography

Optical computing

Back to Top