A Substrate-Independent Framework to Characterise Reservoir Computers

Matthew Dale; Julian F. Miller; Susan Stepney; Martin A. Trefzer

A Substrate-Independent Framework to Characterise Reservoir Computers

Matthew Dale, Julian F. Miller, Susan Stepney, Martin A. Trefzer

Research output: Working paper › Preprint

Abstract

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 that can be used to characterise the quality of any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can also help map the non-trivial relationship between properties and task performance. And through quality, we may even be able to predict the performance of similarly behaved substrates. Applying the framework, we can explain why a previously investigated carbon nanotube/polymer composite performs modestly on tasks, due to a poor quality. In the wider context, the framework offers a greater understanding to what makes a dynamical system compute, helping improve the design of future substrates for RC.

Original language	English
Publisher	arXiv
Number of pages	19
Publication status	Published - 16 Oct 2018

Keywords

cs.ET

Access to Document

1810.07135v1Other version, 7.28 MB

https://arxiv.org/abs/1810.07135

Cite this

@techreport{1ec57210b0e7418f95678de411b8fb32,

title = "A Substrate-Independent Framework to Characterise Reservoir Computers",

abstract = " 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 that can be used to characterise the quality of any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can also help map the non-trivial relationship between properties and task performance. And through quality, we may even be able to predict the performance of similarly behaved substrates. Applying the framework, we can explain why a previously investigated carbon nanotube/polymer composite performs modestly on tasks, due to a poor quality. In the wider context, the framework offers a greater understanding to what makes a dynamical system compute, helping improve the design of future substrates for RC. ",

keywords = "cs.ET",

author = "Matthew Dale and Miller, {Julian F.} and Susan Stepney and Trefzer, {Martin A.}",

year = "2018",

month = oct,

day = "16",

language = "English",

publisher = "arXiv",

type = "WorkingPaper",

institution = "arXiv",

}

TY - UNPB

T1 - A Substrate-Independent Framework to Characterise Reservoir Computers

AU - Dale, Matthew

AU - Miller, Julian F.

AU - Stepney, Susan

AU - Trefzer, Martin A.

PY - 2018/10/16

Y1 - 2018/10/16

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 that can be used to characterise the quality of any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can also help map the non-trivial relationship between properties and task performance. And through quality, we may even be able to predict the performance of similarly behaved substrates. Applying the framework, we can explain why a previously investigated carbon nanotube/polymer composite performs modestly on tasks, due to a poor quality. In the wider context, the framework offers a greater understanding 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 that can be used to characterise the quality of any substrate for RC. Our framework reveals that a definition of quality is not only useful to compare substrates, but can also help map the non-trivial relationship between properties and task performance. And through quality, we may even be able to predict the performance of similarly behaved substrates. Applying the framework, we can explain why a previously investigated carbon nanotube/polymer composite performs modestly on tasks, due to a poor quality. In the wider context, the framework offers a greater understanding to what makes a dynamical system compute, helping improve the design of future substrates for RC.

KW - cs.ET

M3 - Preprint

BT - A Substrate-Independent Framework to Characterise Reservoir Computers

PB - arXiv

ER -