Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates

Zhigang Zeng; Jun Wang

doi:10.1109/IJCNN.2009.5178784

Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates

Zhigang Zeng, Jun Wang

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

This paper presents a new design procedure for the synthesis of associative memories based on cellular neural networks characterized by input and output matrices obtained based on cloning templates by solving a set of inequalities. The design parameters are few even though the dimension of patterns may be very high. The design procedure enables heteroassociative or autoassociative memories to be synthesized with assured global exponential stability and feeding retrieval probes via external inputs rather than initial conditions. Two specific examples are shown to illustrate the applicability of the methodology. ©2009 IEEE.

Original language	English
Title of host publication	Proceedings of the International Joint Conference on Neural Networks
Pages	3504-3511
DOIs	https://doi.org/10.1109/IJCNN.2009.5178784
Publication status	Published - 2009
Externally published	Yes
Event	2009 International Joint Conference on Neural Networks, IJCNN 2009 - Atlanta, GA, United States Duration: 14 Jun 2009 → 19 Jun 2009

Conference

Conference	2009 International Joint Conference on Neural Networks, IJCNN 2009
Country/Territory	United States
City	Atlanta, GA
Period	14/06/09 → 19/06/09

Access Output

10.1109/IJCNN.2009.5178784

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{5a59e92e6dc14c9ca773ca05b3711c73,

title = "Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates",

abstract = "This paper presents a new design procedure for the synthesis of associative memories based on cellular neural networks characterized by input and output matrices obtained based on cloning templates by solving a set of inequalities. The design parameters are few even though the dimension of patterns may be very high. The design procedure enables heteroassociative or autoassociative memories to be synthesized with assured global exponential stability and feeding retrieval probes via external inputs rather than initial conditions. Two specific examples are shown to illustrate the applicability of the methodology. {\textcopyright}2009 IEEE.",

author = "Zhigang Zeng and Jun Wang",

year = "2009",

doi = "10.1109/IJCNN.2009.5178784",

language = "English",

isbn = "9781424435531",

pages = "3504--3511",

booktitle = "Proceedings of the International Joint Conference on Neural Networks",

note = "2009 International Joint Conference on Neural Networks, IJCNN 2009 ; Conference date: 14-06-2009 Through 19-06-2009",

}

Zeng, Z & Wang, J 2009, Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates. in Proceedings of the International Joint Conference on Neural Networks., 5178784, pp. 3504-3511, 2009 International Joint Conference on Neural Networks, IJCNN 2009, Atlanta, GA, United States, 14/06/09. https://doi.org/10.1109/IJCNN.2009.5178784

Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates. / Zeng, Zhigang; Wang, Jun.
Proceedings of the International Joint Conference on Neural Networks. 2009. p. 3504-3511 5178784.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates

AU - Zeng, Zhigang

AU - Wang, Jun

PY - 2009

Y1 - 2009

N2 - This paper presents a new design procedure for the synthesis of associative memories based on cellular neural networks characterized by input and output matrices obtained based on cloning templates by solving a set of inequalities. The design parameters are few even though the dimension of patterns may be very high. The design procedure enables heteroassociative or autoassociative memories to be synthesized with assured global exponential stability and feeding retrieval probes via external inputs rather than initial conditions. Two specific examples are shown to illustrate the applicability of the methodology. ©2009 IEEE.

AB - This paper presents a new design procedure for the synthesis of associative memories based on cellular neural networks characterized by input and output matrices obtained based on cloning templates by solving a set of inequalities. The design parameters are few even though the dimension of patterns may be very high. The design procedure enables heteroassociative or autoassociative memories to be synthesized with assured global exponential stability and feeding retrieval probes via external inputs rather than initial conditions. Two specific examples are shown to illustrate the applicability of the methodology. ©2009 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=70449431511&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-70449431511&origin=recordpage

U2 - 10.1109/IJCNN.2009.5178784

DO - 10.1109/IJCNN.2009.5178784

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 9781424435531

SP - 3504

EP - 3511

BT - Proceedings of the International Joint Conference on Neural Networks

T2 - 2009 International Joint Conference on Neural Networks, IJCNN 2009

Y2 - 14 June 2009 through 19 June 2009

ER -

Analysis and design of associative memories based on cellular neural networks with space-invariant cloning templates

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this