Global optimization through time-varying cellular neural networks

M. Gilli, P. P. Civalleri, T. Roska, L. O. Chua

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The global optimization properties of a cellular neural network (CNN) with a slowly varying slope of the output characteristic (see [1]), are studied. It is shown that a two-cell CNN is able to find the global minimum of a quadratic function over the unit hypercube for any values of the input parameters. Then it is proved that if the dimension is higher than 2, then even the CNN described by the simplest one-dimensional space-invariant template [A1, A0, 1[ fails to find the global minimum in a subset of the parameter space. Finally through extensive simulations, it is shown that the CNN described by the above 3 element template works correctly within several parameter ranges, but that if the parameters are chosen according to a random algorithm, the error rate increases with the number of cells.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications
PublisherIEEE
Pages417-422
Number of pages6
Publication statusPublished - 1996
EventProceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96 - Seville, Spain
Duration: Jun 24 1996Jun 26 1996

Other

OtherProceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96
CitySeville, Spain
Period6/24/966/26/96

Fingerprint

Cellular neural networks
Global optimization

ASJC Scopus subject areas

  • Software

Cite this

Gilli, M., Civalleri, P. P., Roska, T., & Chua, L. O. (1996). Global optimization through time-varying cellular neural networks. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications (pp. 417-422). IEEE.

Global optimization through time-varying cellular neural networks. / Gilli, M.; Civalleri, P. P.; Roska, T.; Chua, L. O.

Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1996. p. 417-422.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Gilli, M, Civalleri, PP, Roska, T & Chua, LO 1996, Global optimization through time-varying cellular neural networks. in Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, pp. 417-422, Proceedings of the 1996 4th IEEE International Workshop on Cellular Neural Networks, and Their Applications, CNNA-96, Seville, Spain, 6/24/96.
Gilli M, Civalleri PP, Roska T, Chua LO. Global optimization through time-varying cellular neural networks. In Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE. 1996. p. 417-422
Gilli, M. ; Civalleri, P. P. ; Roska, T. ; Chua, L. O. / Global optimization through time-varying cellular neural networks. Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications. IEEE, 1996. pp. 417-422
@inproceedings{db8f8dde50564a43a977b2979dd76096,
title = "Global optimization through time-varying cellular neural networks",
abstract = "The global optimization properties of a cellular neural network (CNN) with a slowly varying slope of the output characteristic (see [1]), are studied. It is shown that a two-cell CNN is able to find the global minimum of a quadratic function over the unit hypercube for any values of the input parameters. Then it is proved that if the dimension is higher than 2, then even the CNN described by the simplest one-dimensional space-invariant template [A1, A0, 1[ fails to find the global minimum in a subset of the parameter space. Finally through extensive simulations, it is shown that the CNN described by the above 3 element template works correctly within several parameter ranges, but that if the parameters are chosen according to a random algorithm, the error rate increases with the number of cells.",
author = "M. Gilli and Civalleri, {P. P.} and T. Roska and Chua, {L. O.}",
year = "1996",
language = "English",
pages = "417--422",
booktitle = "Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications",
publisher = "IEEE",

}

TY - GEN

T1 - Global optimization through time-varying cellular neural networks

AU - Gilli, M.

AU - Civalleri, P. P.

AU - Roska, T.

AU - Chua, L. O.

PY - 1996

Y1 - 1996

N2 - The global optimization properties of a cellular neural network (CNN) with a slowly varying slope of the output characteristic (see [1]), are studied. It is shown that a two-cell CNN is able to find the global minimum of a quadratic function over the unit hypercube for any values of the input parameters. Then it is proved that if the dimension is higher than 2, then even the CNN described by the simplest one-dimensional space-invariant template [A1, A0, 1[ fails to find the global minimum in a subset of the parameter space. Finally through extensive simulations, it is shown that the CNN described by the above 3 element template works correctly within several parameter ranges, but that if the parameters are chosen according to a random algorithm, the error rate increases with the number of cells.

AB - The global optimization properties of a cellular neural network (CNN) with a slowly varying slope of the output characteristic (see [1]), are studied. It is shown that a two-cell CNN is able to find the global minimum of a quadratic function over the unit hypercube for any values of the input parameters. Then it is proved that if the dimension is higher than 2, then even the CNN described by the simplest one-dimensional space-invariant template [A1, A0, 1[ fails to find the global minimum in a subset of the parameter space. Finally through extensive simulations, it is shown that the CNN described by the above 3 element template works correctly within several parameter ranges, but that if the parameters are chosen according to a random algorithm, the error rate increases with the number of cells.

UR - http://www.scopus.com/inward/record.url?scp=0030379730&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030379730&partnerID=8YFLogxK

M3 - Conference contribution

SP - 417

EP - 422

BT - Proceedings of the IEEE International Workshop on Cellular Neural Networks and their Applications

PB - IEEE

ER -