Ergodicity, lack thereof, and the performance of reservoir computing with memristive networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baccetti, Valentina, Zhu, Ruomin, Kuncic, Zdenka, Caravelli, Francesco
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910411563991040
author Baccetti, Valentina
Zhu, Ruomin
Kuncic, Zdenka
Caravelli, Francesco
author_facet Baccetti, Valentina
Zhu, Ruomin
Kuncic, Zdenka
Caravelli, Francesco
contents Networks composed of nanoscale memristive components, such as nanowire and nanoparticle networks, have recently received considerable attention because of their potential use as neuromorphic devices. In this study, we explore the connection between ergodicity in memristive and nanowire networks, showing that the performance of reservoir devices improves when these networks are tuned to operate at the edge between two global stability points. The lack of ergodicity is associated with the emergence of memory in the system. We measure the level of ergodicity using the Thirumalai-Mountain metric, and we show that in the absence of ergodicity, two memristive systems show improved performance when utilized as reservoir computers (RC). In particular, we highlight that it is also important to let the system synchronize to the input signal in order for the performance of the RC to exhibit improvements over the baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2310_09530
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Ergodicity, lack thereof, and the performance of reservoir computing with memristive networks
Baccetti, Valentina
Zhu, Ruomin
Kuncic, Zdenka
Caravelli, Francesco
Disordered Systems and Neural Networks
Statistical Mechanics
Networks composed of nanoscale memristive components, such as nanowire and nanoparticle networks, have recently received considerable attention because of their potential use as neuromorphic devices. In this study, we explore the connection between ergodicity in memristive and nanowire networks, showing that the performance of reservoir devices improves when these networks are tuned to operate at the edge between two global stability points. The lack of ergodicity is associated with the emergence of memory in the system. We measure the level of ergodicity using the Thirumalai-Mountain metric, and we show that in the absence of ergodicity, two memristive systems show improved performance when utilized as reservoir computers (RC). In particular, we highlight that it is also important to let the system synchronize to the input signal in order for the performance of the RC to exhibit improvements over the baseline.
title Ergodicity, lack thereof, and the performance of reservoir computing with memristive networks
topic Disordered Systems and Neural Networks
Statistical Mechanics
url https://arxiv.org/abs/2310.09530