Share Email Print

Proceedings Paper

Electronic Neural Networks For Global Optimization
Author(s): A. P. Thakoor; A. W. Moopenn; S. Eberhardt
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

An electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.

Paper Details

Date Published: 1 February 1990
PDF: 8 pages
Proc. SPIE 1196, Intelligent Control and Adaptive Systems, (1 February 1990); doi: 10.1117/12.969917
Show Author Affiliations
A. P. Thakoor, California Institute of Technology (United States)
A. W. Moopenn, California Institute of Technology (United States)
S. Eberhardt, California Institute of Technology (United States)

Published in SPIE Proceedings Vol. 1196:
Intelligent Control and Adaptive Systems
Guillermo Rodriguez, Editor(s)

© SPIE. Terms of Use
Back to Top