Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural Networks.

Zhang, J; Zhu, S; Bao, G; Liu, X; Wen, S

Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural Networks.

Zhang, J Zhu, S Bao, G Liu, X Wen, S

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Journal Article
Citation:: IEEE Transactions on Cybernetics, 2022, PP, (12), pp. 12989-13000
Issue Date:: 2022-08-04

Closed Access

	Filename	Description	Size
	Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural Networks.pdf	Published version	2.21 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zhang, J
dc.contributor.author	Zhu, S
dc.contributor.author	Bao, G
dc.contributor.author	Liu, X
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.date.accessioned	2023-02-28T03:37:20Z
dc.date.available	2023-02-28T03:37:20Z
dc.date.issued	2022-08-04
dc.identifier.citation	IEEE Transactions on Cybernetics, 2022, PP, (12), pp. 12989-13000
dc.identifier.issn	1083-4419
dc.identifier.issn	2168-2275
dc.identifier.uri	http://hdl.handle.net/10453/166527
dc.description.abstract	This article aims at analyzing and designing the multivalued high-capacity-associative memories based on recurrent neural networks with both asynchronous and distributed delays. In order to increase storage capacities, multivalued activation functions are introduced into associative memories. The stored patterns are retrieved by external input vectors instead of initial conditions, which can guarantee accurate associative memories by avoiding spurious equilibrium points. Some sufficient conditions are proposed to ensure the existence, uniqueness, and global exponential stability of the equilibrium point of neural networks with mixed delays. For neural networks with n neurons, m-dimensional input vectors, and 2k-valued activation functions, the autoassociative memories have (2k)n storage capacities and heteroassociative memories have min storage capacities. That is, the storage capacities of designed associative memories in this article are obviously higher than the 2n and min storage capacities of the conventional ones. Three examples are given to support the theoretical results.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Institute of Electrical and Electronics Engineers
dc.relation.ispartof	IEEE Transactions on Cybernetics
dc.relation.isbasedon	10.1109/TCYB.2021.3095499
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0102 Applied Mathematics, 0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.mesh	Algorithms
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Time Factors
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Neurons
dc.subject.mesh	Neurons
dc.subject.mesh	Algorithms
dc.subject.mesh	Time Factors
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Algorithms
dc.subject.mesh	Computer Simulation
dc.subject.mesh	Time Factors
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Neurons
dc.title	Analysis and Design of Multivalued High-Capacity Associative Memories Based on Delayed Recurrent Neural Networks.
dc.type	Journal Article
utslib.citation.volume	PP
utslib.location.activity	United States
utslib.for	0102 Applied Mathematics
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-02-28T03:37:19Z
pubs.issue	12
pubs.publication-status	Published online
pubs.volume	PP
utslib.citation.issue	12

Abstract:

This article aims at analyzing and designing the multivalued high-capacity-associative memories based on recurrent neural networks with both asynchronous and distributed delays. In order to increase storage capacities, multivalued activation functions are introduced into associative memories. The stored patterns are retrieved by external input vectors instead of initial conditions, which can guarantee accurate associative memories by avoiding spurious equilibrium points. Some sufficient conditions are proposed to ensure the existence, uniqueness, and global exponential stability of the equilibrium point of neural networks with mixed delays. For neural networks with n neurons, m-dimensional input vectors, and 2k-valued activation functions, the autoassociative memories have (2k)n storage capacities and heteroassociative memories have min storage capacities. That is, the storage capacities of designed associative memories in this article are obviously higher than the 2n and min storage capacities of the conventional ones. Three examples are given to support the theoretical results.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/166527