Forgetting memristor based STDP learning circuit for neural networks.

Zhou, W; Wen, S; Liu, Y; Liu, L; Liu, X; Chen, L

Forgetting memristor based STDP learning circuit for neural networks.

Zhou, W Wen, S

Liu, Y Liu, L Liu, X Chen, L

Permalink

Publisher:: Elsevier
Publication Type:: Journal Article
Citation:: Neural Netw, 2023, 158, pp. 293-304
Issue Date:: 2023-01

Closed Access

	Filename	Description	Size
	1-s2.0-S0893608022004646-main.pdf	Published version	2.37 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	Zhou, W
dc.contributor.author	Wen, S https://orcid.org/0000-0001-8077-7001
dc.contributor.author	Liu, Y
dc.contributor.author	Liu, L
dc.contributor.author	Liu, X
dc.contributor.author	Chen, L
dc.date.accessioned	2023-03-13T12:54:14Z
dc.date.available	2022-11-14
dc.date.available	2023-03-13T12:54:14Z
dc.date.issued	2023-01
dc.identifier.citation	Neural Netw, 2023, 158, pp. 293-304
dc.identifier.issn	0893-6080
dc.identifier.issn	1879-2782
dc.identifier.uri	http://hdl.handle.net/10453/167170
dc.description.abstract	The circuit implementation of STDP based on memristor is of great significance for the application of neural network. However, recent research shows that the research on the pure circuit implementation of forgetting memristor and STDP is still rare. This paper proposes a new STDP learning rule implementation circuit based on the forgetting memristor. This kind of forgetting memory resistance synapse makes the neural network have the function of time-division multiplexing, but the instability of short-term memory will affect the learning ability of the neural network. This paper analyzes and discusses the influence of synapses with long-term and short-term memory on the learning characteristics of neural network STDP, which lays a foundation for the construction of time-division multiplexing neural network with long-term and short-term memory synapses. Through this circuit, it is found that the volatile memristor has different behaviors to the stimulus signal in different initial states, and the resulting LTP phenomenon is more in line with the forgetting effect in biology. This circuit has multiple adjustable parameters, which can fit the STDP learning rules under different conditions. The application of neural network proves the availability of this circuit.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	Elsevier
dc.relation.ispartof	Neural Netw
dc.relation.isbasedon	10.1016/j.neunet.2022.11.023
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.mesh	Neuronal Plasticity
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Synapses
dc.subject.mesh	Learning
dc.subject.mesh	Memory, Short-Term
dc.subject.mesh	Synapses
dc.subject.mesh	Learning
dc.subject.mesh	Memory, Short-Term
dc.subject.mesh	Neuronal Plasticity
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Neuronal Plasticity
dc.subject.mesh	Neural Networks, Computer
dc.subject.mesh	Synapses
dc.subject.mesh	Learning
dc.subject.mesh	Memory, Short-Term
dc.title	Forgetting memristor based STDP learning circuit for neural networks.
dc.type	Journal Article
utslib.citation.volume	158
utslib.location.activity	United States
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	2023-03-13T12:54:12Z
pubs.publication-status	Published
pubs.volume	158

Abstract:

The circuit implementation of STDP based on memristor is of great significance for the application of neural network. However, recent research shows that the research on the pure circuit implementation of forgetting memristor and STDP is still rare. This paper proposes a new STDP learning rule implementation circuit based on the forgetting memristor. This kind of forgetting memory resistance synapse makes the neural network have the function of time-division multiplexing, but the instability of short-term memory will affect the learning ability of the neural network. This paper analyzes and discusses the influence of synapses with long-term and short-term memory on the learning characteristics of neural network STDP, which lays a foundation for the construction of time-division multiplexing neural network with long-term and short-term memory synapses. Through this circuit, it is found that the volatile memristor has different behaviors to the stimulus signal in different initial states, and the resulting LTP phenomenon is more in line with the forgetting effect in biology. This circuit has multiple adjustable parameters, which can fit the STDP learning rules under different conditions. The application of neural network proves the availability of this circuit.

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

http://hdl.handle.net/10453/167170