Reservoir computing using networks of memristors: effects of topology and heterogeneity.

Mallinson, JB; Heywood, ZE; Daniels, RK; Arnold, MD; Bones, PJ; Brown, SA

Reservoir computing using networks of memristors: effects of topology and heterogeneity.

Mallinson, JB Heywood, ZE Daniels, RK Arnold, MD Bones, PJ Brown, SA

Permalink

Publisher:: ROYAL SOC CHEMISTRY
Publication Type:: Journal Article
Citation:: Nanoscale, 2023, 15, (22), pp. 9663-9674
Issue Date:: 2023-06-08

Embargoed

	Filename	Description	Size
	Reservoir computing using networks of memristors (Accept Manuscript).pdf	Accepted version	1.6 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Embargoed
Open Access

This item is currently unavailable due to the publisher's embargo.

The embargo period expires on 8 Jun 2024

Full metadata record

Field	Value	Language
dc.contributor.author	Mallinson, JB
dc.contributor.author	Heywood, ZE
dc.contributor.author	Daniels, RK
dc.contributor.author	Arnold, MD
dc.contributor.author	Bones, PJ
dc.contributor.author	Brown, SA
dc.date.accessioned	2024-01-16T01:34:44Z
dc.date.available	2024-01-16T01:34:44Z
dc.date.issued	2023-06-08
dc.identifier.citation	Nanoscale, 2023, 15, (22), pp. 9663-9674
dc.identifier.issn	2040-3364
dc.identifier.issn	2040-3372
dc.identifier.uri	http://hdl.handle.net/10453/174543
dc.description.abstract	Reservoir computing (RC) has attracted significant interest as a framework for the implementation of novel neuromorphic computing architectures. Previously attention has been focussed on software-based reservoirs, where it has been demonstrated that reservoir topology plays a role in task performance, and functional advantage has been attributed to small-world and scale-free connectivity. However in hardware systems, such as electronic memristor networks, the mechanisms responsible for the reservoir dynamics are very different and the role of reservoir topology is largely unknown. Here we compare the performance of a range of memristive reservoirs in several RC tasks that are chosen to highlight different system requirements. We focus on percolating networks of nanoparticles (PNNs) which are novel self-assembled nanoscale systems that exhibit scale-free and small-world properties. We find that the performance of regular arrays of uniform memristive elements is limited by their symmetry but that this symmetry can be broken either by a heterogeneous distribution of memristor properties or a scale-free topology. The best perfomance across all tasks is observed for a scale-free network with uniform memistor properties. These results provide insight into the role of topology in neuromorphic reservoirs as well as an overview of the computational performance of scale-free networks of memristors in a range of benchmark tasks.
dc.format	Electronic
dc.language	eng
dc.publisher	ROYAL SOC CHEMISTRY
dc.relation.ispartof	Nanoscale
dc.relation.isbasedon	10.1039/d2nr07275k
dc.rights	info:eu-repo/semantics/embargoedAccess
dc.subject	02 Physical Sciences, 03 Chemical Sciences, 10 Technology
dc.subject.classification	Nanoscience & Nanotechnology
dc.subject.classification	34 Chemical sciences
dc.subject.classification	40 Engineering
dc.subject.classification	51 Physical sciences
dc.title	Reservoir computing using networks of memristors: effects of topology and heterogeneity.
dc.type	Journal Article
utslib.citation.volume	15
utslib.location.activity	England
utslib.for	02 Physical Sciences
utslib.for	03 Chemical Sciences
utslib.for	10 Technology
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Science/School of Mathematical and Physical Sciences
utslib.copyright.status	embargoed	*
utslib.copyright.embargo	2024-06-08T00:00:00+1000Z
dc.date.updated	2024-01-16T01:34:43Z
pubs.issue	22
pubs.publication-status	Published online
pubs.volume	15
utslib.citation.issue	22

Abstract:

Reservoir computing (RC) has attracted significant interest as a framework for the implementation of novel neuromorphic computing architectures. Previously attention has been focussed on software-based reservoirs, where it has been demonstrated that reservoir topology plays a role in task performance, and functional advantage has been attributed to small-world and scale-free connectivity. However in hardware systems, such as electronic memristor networks, the mechanisms responsible for the reservoir dynamics are very different and the role of reservoir topology is largely unknown. Here we compare the performance of a range of memristive reservoirs in several RC tasks that are chosen to highlight different system requirements. We focus on percolating networks of nanoparticles (PNNs) which are novel self-assembled nanoscale systems that exhibit scale-free and small-world properties. We find that the performance of regular arrays of uniform memristive elements is limited by their symmetry but that this symmetry can be broken either by a heterogeneous distribution of memristor properties or a scale-free topology. The best perfomance across all tasks is observed for a scale-free network with uniform memistor properties. These results provide insight into the role of topology in neuromorphic reservoirs as well as an overview of the computational performance of scale-free networks of memristors in a range of benchmark tasks.

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

http://hdl.handle.net/10453/174543