Realization of limit cycles by neural networks with piecewise linear activation function

Norikazu Takahashi, Tsuyoshi Yamakawa, Tetsuo Nishi

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

3 Citations (Scopus)

Abstract

A simple method of realizing a prescribed limit cycle by means of a continuous-time recurrent neural network with the piecewise-linear activation function is proposed. Since the proposed method is formulated as a set of linear inequalities, we can easily determine parameters of the network by using, for example, the simplex method.

Original languageEnglish
Title of host publicationProceedings of the 2005 European Conference on Circuit Theory and Design
Pages7-10
Number of pages4
Volume3
DOIs
Publication statusPublished - 2005
Externally publishedYes
Event2005 European Conference on Circuit Theory and Design - Cork, Ireland
Duration: Aug 28 2005Sep 2 2005

Other

Other2005 European Conference on Circuit Theory and Design
CountryIreland
CityCork
Period8/28/059/2/05

Fingerprint

Recurrent neural networks
Chemical activation
Neural networks

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Takahashi, N., Yamakawa, T., & Nishi, T. (2005). Realization of limit cycles by neural networks with piecewise linear activation function. In Proceedings of the 2005 European Conference on Circuit Theory and Design (Vol. 3, pp. 7-10). [1523047] https://doi.org/10.1109/ECCTD.2005.1523047

Realization of limit cycles by neural networks with piecewise linear activation function. / Takahashi, Norikazu; Yamakawa, Tsuyoshi; Nishi, Tetsuo.

Proceedings of the 2005 European Conference on Circuit Theory and Design. Vol. 3 2005. p. 7-10 1523047.

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

Takahashi, N, Yamakawa, T & Nishi, T 2005, Realization of limit cycles by neural networks with piecewise linear activation function. in Proceedings of the 2005 European Conference on Circuit Theory and Design. vol. 3, 1523047, pp. 7-10, 2005 European Conference on Circuit Theory and Design, Cork, Ireland, 8/28/05. https://doi.org/10.1109/ECCTD.2005.1523047
Takahashi N, Yamakawa T, Nishi T. Realization of limit cycles by neural networks with piecewise linear activation function. In Proceedings of the 2005 European Conference on Circuit Theory and Design. Vol. 3. 2005. p. 7-10. 1523047 https://doi.org/10.1109/ECCTD.2005.1523047
Takahashi, Norikazu ; Yamakawa, Tsuyoshi ; Nishi, Tetsuo. / Realization of limit cycles by neural networks with piecewise linear activation function. Proceedings of the 2005 European Conference on Circuit Theory and Design. Vol. 3 2005. pp. 7-10
@inproceedings{1c9c7a0d21774d6f999e6f61989b0219,
title = "Realization of limit cycles by neural networks with piecewise linear activation function",
abstract = "A simple method of realizing a prescribed limit cycle by means of a continuous-time recurrent neural network with the piecewise-linear activation function is proposed. Since the proposed method is formulated as a set of linear inequalities, we can easily determine parameters of the network by using, for example, the simplex method.",
author = "Norikazu Takahashi and Tsuyoshi Yamakawa and Tetsuo Nishi",
year = "2005",
doi = "10.1109/ECCTD.2005.1523047",
language = "English",
isbn = "0780390660",
volume = "3",
pages = "7--10",
booktitle = "Proceedings of the 2005 European Conference on Circuit Theory and Design",

}

TY - GEN

T1 - Realization of limit cycles by neural networks with piecewise linear activation function

AU - Takahashi, Norikazu

AU - Yamakawa, Tsuyoshi

AU - Nishi, Tetsuo

PY - 2005

Y1 - 2005

N2 - A simple method of realizing a prescribed limit cycle by means of a continuous-time recurrent neural network with the piecewise-linear activation function is proposed. Since the proposed method is formulated as a set of linear inequalities, we can easily determine parameters of the network by using, for example, the simplex method.

AB - A simple method of realizing a prescribed limit cycle by means of a continuous-time recurrent neural network with the piecewise-linear activation function is proposed. Since the proposed method is formulated as a set of linear inequalities, we can easily determine parameters of the network by using, for example, the simplex method.

UR - http://www.scopus.com/inward/record.url?scp=33749022788&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33749022788&partnerID=8YFLogxK

U2 - 10.1109/ECCTD.2005.1523047

DO - 10.1109/ECCTD.2005.1523047

M3 - Conference contribution

AN - SCOPUS:33749022788

SN - 0780390660

SN - 9780780390669

VL - 3

SP - 7

EP - 10

BT - Proceedings of the 2005 European Conference on Circuit Theory and Design

ER -