Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories

Ryota Horie, E. Aiyoshi

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

4 Citations (Scopus)

Abstract

We propose a new mutually coupled plural Neural Networks (N.N.) modules and its application to associative memories from the view point of noncooperative game theory. First, We propose a new dynamical searching model named Parallel Steepest Descent Method with Braking operators (PSDMB) which searches the Nash Equilibrium (NE) points under [0, 1]-interval or nonnegative constraints. Second, we propose a new mutually coupled plural N.N. modules named Game Neural Networks (GNN) to realize the proposed PSDMB with quadratic objective functions. In Addition, we indicate relations between the PSDMB, the GNN and the Lotka-Volterra equation. Last, for an application of the proposed GNN, we propose two kinds of multi modular associative memories which can associate the combined patterns composed of plural partial patterns: (1) the combined patterns are stored as the NE points and robust for noisy inputs; (2) the circulative sequence of the combined patterns are stored as saddles of a heteroclinic cycle.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Pages1886-1891
Number of pages6
Volume2
Publication statusPublished - 1998
Externally publishedYes
EventProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5) - San Diego, CA, USA
Duration: 1998 Oct 111998 Oct 14

Other

OtherProceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5)
CitySan Diego, CA, USA
Period98/10/1198/10/14

Fingerprint

Steepest descent method
Neural networks
Data storage equipment
Braking
Game theory

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Cite this

Horie, R., & Aiyoshi, E. (1998). Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 2, pp. 1886-1891). IEEE.

Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories. / Horie, Ryota; Aiyoshi, E.

Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 1998. p. 1886-1891.

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

Horie, R & Aiyoshi, E 1998, Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories. in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. vol. 2, IEEE, pp. 1886-1891, Proceedings of the 1998 IEEE International Conference on Systems, Man, and Cybernetics. Part 2 (of 5), San Diego, CA, USA, 98/10/11.
Horie R, Aiyoshi E. Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2. IEEE. 1998. p. 1886-1891
Horie, Ryota ; Aiyoshi, E. / Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories. Proceedings of the IEEE International Conference on Systems, Man and Cybernetics. Vol. 2 IEEE, 1998. pp. 1886-1891
@inproceedings{61df4f3b6a5b473792343b65f01a533d,
title = "Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories",
abstract = "We propose a new mutually coupled plural Neural Networks (N.N.) modules and its application to associative memories from the view point of noncooperative game theory. First, We propose a new dynamical searching model named Parallel Steepest Descent Method with Braking operators (PSDMB) which searches the Nash Equilibrium (NE) points under [0, 1]-interval or nonnegative constraints. Second, we propose a new mutually coupled plural N.N. modules named Game Neural Networks (GNN) to realize the proposed PSDMB with quadratic objective functions. In Addition, we indicate relations between the PSDMB, the GNN and the Lotka-Volterra equation. Last, for an application of the proposed GNN, we propose two kinds of multi modular associative memories which can associate the combined patterns composed of plural partial patterns: (1) the combined patterns are stored as the NE points and robust for noisy inputs; (2) the circulative sequence of the combined patterns are stored as saddles of a heteroclinic cycle.",
author = "Ryota Horie and E. Aiyoshi",
year = "1998",
language = "English",
volume = "2",
pages = "1886--1891",
booktitle = "Proceedings of the IEEE International Conference on Systems, Man and Cybernetics",
publisher = "IEEE",

}

TY - GEN

T1 - Neural Networks realization of searching models for Nash Equilibrium points and their application to associative memories

AU - Horie, Ryota

AU - Aiyoshi, E.

PY - 1998

Y1 - 1998

N2 - We propose a new mutually coupled plural Neural Networks (N.N.) modules and its application to associative memories from the view point of noncooperative game theory. First, We propose a new dynamical searching model named Parallel Steepest Descent Method with Braking operators (PSDMB) which searches the Nash Equilibrium (NE) points under [0, 1]-interval or nonnegative constraints. Second, we propose a new mutually coupled plural N.N. modules named Game Neural Networks (GNN) to realize the proposed PSDMB with quadratic objective functions. In Addition, we indicate relations between the PSDMB, the GNN and the Lotka-Volterra equation. Last, for an application of the proposed GNN, we propose two kinds of multi modular associative memories which can associate the combined patterns composed of plural partial patterns: (1) the combined patterns are stored as the NE points and robust for noisy inputs; (2) the circulative sequence of the combined patterns are stored as saddles of a heteroclinic cycle.

AB - We propose a new mutually coupled plural Neural Networks (N.N.) modules and its application to associative memories from the view point of noncooperative game theory. First, We propose a new dynamical searching model named Parallel Steepest Descent Method with Braking operators (PSDMB) which searches the Nash Equilibrium (NE) points under [0, 1]-interval or nonnegative constraints. Second, we propose a new mutually coupled plural N.N. modules named Game Neural Networks (GNN) to realize the proposed PSDMB with quadratic objective functions. In Addition, we indicate relations between the PSDMB, the GNN and the Lotka-Volterra equation. Last, for an application of the proposed GNN, we propose two kinds of multi modular associative memories which can associate the combined patterns composed of plural partial patterns: (1) the combined patterns are stored as the NE points and robust for noisy inputs; (2) the circulative sequence of the combined patterns are stored as saddles of a heteroclinic cycle.

UR - http://www.scopus.com/inward/record.url?scp=0032319841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032319841&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1886

EP - 1891

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

PB - IEEE

ER -