A substrate-independent framework to characterize reservoir computers

TY - JOUR

T1 - A substrate-independent framework to characterize reservoir computers

AU - Dale, Matthew

AU - Miller, Julian Francis

AU - Stepney, Susan

AU - Trefzer, Martin Albrecht

N1 - © 2019 The Authors.

PY - 2019/6/28

Y1 - 2019/6/28

N2 - The Reservoir Computing (RC) framework states that any non-linear, input-driven dynamical system (the reservoir) exhibiting properties such as a fading memory and input separability can be trained to perform computational tasks. This broad inclusion of systems has led to many new physical substrates for RC. Properties essential for reservoirs to compute are tuned through reconfiguration of the substrate, such as change in virtual topology or physical morphology. As a result, each substrate possesses a unique "quality" - obtained through reconfiguration - to realise different reservoirs for different tasks. Here we describe an experimental framework to characterise the quality of potentially \textit{any} substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can help map the non-trivial relationship between properties and task performance. In the wider context, the framework offers a greater understanding as to what makes a dynamical system compute, helping improve the design of future substrates for RC.

AB - The Reservoir Computing (RC) framework states that any non-linear, input-driven dynamical system (the reservoir) exhibiting properties such as a fading memory and input separability can be trained to perform computational tasks. This broad inclusion of systems has led to many new physical substrates for RC. Properties essential for reservoirs to compute are tuned through reconfiguration of the substrate, such as change in virtual topology or physical morphology. As a result, each substrate possesses a unique "quality" - obtained through reconfiguration - to realise different reservoirs for different tasks. Here we describe an experimental framework to characterise the quality of potentially \textit{any} substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can help map the non-trivial relationship between properties and task performance. In the wider context, the framework offers a greater understanding as to what makes a dynamical system compute, helping improve the design of future substrates for RC.

KW - unconventional computing

KW - evolution in materio

KW - reservoir computing

KW - Carbon Nanotubes (CNTs)

KW - Characterization

KW - Physical computation

KW - Reservoir computing

UR - https://arxiv.org/abs/1810.07135

UR - http://www.scopus.com/inward/record.url?scp=85068260996&partnerID=8YFLogxK

U2 - 10.1098/rspa.2018.0723

DO - 10.1098/rspa.2018.0723

M3 - Article

SN - 1364-5021

VL - 475

JO - Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences

JF - Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences

IS - 2226

M1 - 20180723

ER -