A full-function Pavlov associative memory implementation with memristance changing circuit

Yang, L; Zeng, Z; Wen, S

A full-function Pavlov associative memory implementation with memristance changing circuit

Yang, L Zeng, Z Wen, S

Permalink

Publisher:: ELSEVIER SCIENCE BV
Publication Type:: Journal Article
Citation:: Neurocomputing, 2018, 272, pp. 513-519
Issue Date:: 2018-01-10

Closed Access

	Filename	Description	Size
	1-s2.0-S0925231217312663-main.pdf	Published version	884.48 kB	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	Yang, L
dc.contributor.author	Zeng, Z
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.date.accessioned	2022-09-04T07:30:04Z
dc.date.available	2022-09-04T07:30:04Z
dc.date.issued	2018-01-10
dc.identifier.citation	Neurocomputing, 2018, 272, pp. 513-519
dc.identifier.issn	0925-2312
dc.identifier.issn	1872-8286
dc.identifier.uri	http://hdl.handle.net/10453/161315
dc.description.abstract	Positive voltages and negative voltages are applied to adjust memristance in most memristive circuits. This paper presents a memristance changing circuit in which memristance is changed only by the positive voltage. A mathematical calculation method is proposed to analyze the memristance change approximately. Furthermore, memristance changing circuits are utilized as synapses to construct a neural network to imitate full-function Pavlov associative memory. Compared to the classical Pavlov associative memory, the full-function Pavlov associative memory contains additional food forgetting and ring forgetting processes. The forgetting processes will be triggered in the condition that either the food or the ring is given to the dog after the learning processes. The learning and forgetting time of the associative memory can be obtained by the proposed mathematical calculation method in advance approximately.
dc.language	English
dc.publisher	ELSEVIER SCIENCE BV
dc.relation.ispartof	Neurocomputing
dc.relation.isbasedon	10.1016/j.neucom.2017.07.020
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	08 Information and Computing Sciences, 09 Engineering, 17 Psychology and Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.title	A full-function Pavlov associative memory implementation with memristance changing circuit
dc.type	Journal Article
utslib.citation.volume	272
utslib.for	08 Information and Computing Sciences
utslib.for	09 Engineering
utslib.for	17 Psychology and Cognitive Sciences
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	*
dc.date.updated	2022-09-04T07:30:03Z
pubs.publication-status	Published
pubs.volume	272

Abstract:

Positive voltages and negative voltages are applied to adjust memristance in most memristive circuits. This paper presents a memristance changing circuit in which memristance is changed only by the positive voltage. A mathematical calculation method is proposed to analyze the memristance change approximately. Furthermore, memristance changing circuits are utilized as synapses to construct a neural network to imitate full-function Pavlov associative memory. Compared to the classical Pavlov associative memory, the full-function Pavlov associative memory contains additional food forgetting and ring forgetting processes. The forgetting processes will be triggered in the condition that either the food or the ring is given to the dog after the learning processes. The learning and forgetting time of the associative memory can be obtained by the proposed mathematical calculation method in advance approximately.

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

http://hdl.handle.net/10453/161315