Robustness of attractor networks and an improved convex corner detector

P. Nachbar, A. J. Schuler, T. Füssl, J. A. Nossek, L. O. Chua

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

By defining several notions of robustness for an attractor network, we aie able to augment previous results about the AdaTron algorithm by explicit values for the robustness of the optimal weights. We show, that the symmetry of a problem is reflected by the invariance of the optimal weights. This enables us to deduce that a convex coiner detection, using a discrete-time Cellular Neural Network (DTCNN), can not be accomplished with just one clock cycle, and we propose an improved convex corner detector.

Original languageEnglish
Title of host publicationProceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages55-61
Number of pages7
ISBN (Electronic)0780308751, 9780780308756
DOIs
StatePublished - 1992
Event2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992 - Munich, Germany
Duration: 14 Oct 199216 Oct 1992

Publication series

NameProceedings - 2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992

Conference

Conference2nd International Workshop on Cellular Neural Networks and their Applications, CNNA 1992
Country/TerritoryGermany
CityMunich
Period14/10/9216/10/92

Fingerprint

Dive into the research topics of 'Robustness of attractor networks and an improved convex corner detector'. Together they form a unique fingerprint.

Cite this