Autoassociative memory design using interconnected generalized Brain-State-in-a-Box neural networks

Cheolhwan Oh, Stanislaw H. Zak, Guisheng Zhai

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.

Original languageEnglish
Pages (from-to)181-196
Number of pages16
JournalInternational Journal of Neural Systems
Volume15
Issue number3
DOIs
Publication statusPublished - 2005 Jun
Externally publishedYes

Fingerprint

Linear matrix inequalities
Brain
Neural networks
Data storage equipment
Network architecture
MATLAB

Keywords

  • Associative memory
  • Brain-State-in-a-Box (BSB) neural network
  • Interconnected neural networks
  • Linear matrix inequalities

ASJC Scopus subject areas

  • Computer Networks and Communications

Cite this

Autoassociative memory design using interconnected generalized Brain-State-in-a-Box neural networks. / Oh, Cheolhwan; Zak, Stanislaw H.; Zhai, Guisheng.

In: International Journal of Neural Systems, Vol. 15, No. 3, 06.2005, p. 181-196.

Research output: Contribution to journalArticle

@article{db3c8a1098b64e2d9c96f76f5072c8be,
title = "Autoassociative memory design using interconnected generalized Brain-State-in-a-Box neural networks",
abstract = "A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.",
keywords = "Associative memory, Brain-State-in-a-Box (BSB) neural network, Interconnected neural networks, Linear matrix inequalities",
author = "Cheolhwan Oh and Zak, {Stanislaw H.} and Guisheng Zhai",
year = "2005",
month = "6",
doi = "10.1142/S0129065705000189",
language = "English",
volume = "15",
pages = "181--196",
journal = "International Journal of Neural Systems",
issn = "0129-0657",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "3",

}

TY - JOUR

T1 - Autoassociative memory design using interconnected generalized Brain-State-in-a-Box neural networks

AU - Oh, Cheolhwan

AU - Zak, Stanislaw H.

AU - Zhai, Guisheng

PY - 2005/6

Y1 - 2005/6

N2 - A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.

AB - A class of interconnected neural networks composed of generalized Brain-State-in-a-Box (gBSB) neural subnetworks is considered. Interconnected gBSB neural network architectures are proposed along with their stability conditions. The design of the interconnected neural networks is reduced to the problem of solving linear matrix inequalities (LMIs) to determine the interconnection parameters. A method for solving LMIs is devised generating the solutions that, in general, are further away from zero than the corresponding solutions obtained using MATLAB's LMI toolbox, thus resulting in stronger interconnections between the subnetworks. The proposed architectures are then used to construct neural associative memories. Simulations are performed to illustrate the results obtained.

KW - Associative memory

KW - Brain-State-in-a-Box (BSB) neural network

KW - Interconnected neural networks

KW - Linear matrix inequalities

UR - http://www.scopus.com/inward/record.url?scp=32944465496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=32944465496&partnerID=8YFLogxK

U2 - 10.1142/S0129065705000189

DO - 10.1142/S0129065705000189

M3 - Article

VL - 15

SP - 181

EP - 196

JO - International Journal of Neural Systems

JF - International Journal of Neural Systems

SN - 0129-0657

IS - 3

ER -