A quick search of optimal solutions for cellular neural networks

Sa H. Bang*, Bing J. Sheu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

Hardware annealing, which is a paralleled version of mean-field annealing in analog networks, is an efficient method of finding the optimal solutions for cellular neural networks. It does not require any stochastic procedure and henceforth can be very fast. Once the energy of the network is increased, the hardware annealing searches for the globally minimum energy state by gradually increasing the gain of neurons. In typical non-optimization problems, it also provides enough energy to frozen neurons caused by ill-conditioned initial states.

Original languageEnglish
Title of host publicationWorld Congress on Neural Networks
PublisherTaylor and Francis
PagesII.549-II.554
Volume2
ISBN (Electronic)9781315784076
ISBN (Print)9780805817454
StatePublished - 10 09 2021
Externally publishedYes

Bibliographical note

Publisher Copyright:
© 1994 by Taylor & Francis. All rights reserved.

Fingerprint

Dive into the research topics of 'A quick search of optimal solutions for cellular neural networks'. Together they form a unique fingerprint.

Cite this