Reservoir Computing as a model for in materio computing

Matthew Nicholas Dale; Julian Francis Miller; Susan Stepney

doi:10.1007/978-3-319-33924-5_22

Reservoir Computing as a model for in materio computing

Matthew Nicholas Dale, Julian Francis Miller, Susan Stepney

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Chapter

Abstract

Research in substrate-based computing has shown that materials contain rich properties that can be exploited to solve computational problems. One such technique known as Evolution-in-materio uses evolutionary algorithms to manipulate material substrates for computation. However, in general, modelling the computational processes occurring in such systems is a difficult task and understanding what part of the embodied system is doing the computation is still fairly ill-defined. This chapter discusses the prospects of using Reservoir Computing as a model for in materio computing, introducing new training techniques (taken from Reservoir Computing) that could overcome training difficulties found in the current Evolution-in-Materio technique.

Original language	English
Title of host publication	Advances in Unconventional Computing
Editors	Andrew Adamatsky
Publisher	Springer
Pages	533-571
Volume	1
ISBN (Electronic)	978-3-319-33924-5
DOIs	https://doi.org/10.1007/978-3-319-33924-5_22
Publication status	Published - 2017

Access to Document

10.1007/978-3-319-33924-5_22

Cite this

@inbook{d6a0ac1cb026427499c392ec40538639,

title = "Reservoir Computing as a model for in materio computing",

abstract = "Research in substrate-based computing has shown that materials contain rich properties that can be exploited to solve computational problems. One such technique known as Evolution-in-materio uses evolutionary algorithms to manipulate material substrates for computation. However, in general, modelling the computational processes occurring in such systems is a difficult task and understanding what part of the embodied system is doing the computation is still fairly ill-defined. This chapter discusses the prospects of using Reservoir Computing as a model for in materio computing, introducing new training techniques (taken from Reservoir Computing) that could overcome training difficulties found in the current Evolution-in-Materio technique.",

author = "Dale, {Matthew Nicholas} and Miller, {Julian Francis} and Susan Stepney",

year = "2017",

doi = "10.1007/978-3-319-33924-5_22",

language = "English",

volume = "1",

pages = "533--571",

editor = "Andrew Adamatsky",

booktitle = "Advances in Unconventional Computing",

publisher = "Springer",

address = "Germany",

}

TY - CHAP

T1 - Reservoir Computing as a model for in materio computing

AU - Dale, Matthew Nicholas

AU - Miller, Julian Francis

AU - Stepney, Susan

PY - 2017

Y1 - 2017

N2 - Research in substrate-based computing has shown that materials contain rich properties that can be exploited to solve computational problems. One such technique known as Evolution-in-materio uses evolutionary algorithms to manipulate material substrates for computation. However, in general, modelling the computational processes occurring in such systems is a difficult task and understanding what part of the embodied system is doing the computation is still fairly ill-defined. This chapter discusses the prospects of using Reservoir Computing as a model for in materio computing, introducing new training techniques (taken from Reservoir Computing) that could overcome training difficulties found in the current Evolution-in-Materio technique.

AB - Research in substrate-based computing has shown that materials contain rich properties that can be exploited to solve computational problems. One such technique known as Evolution-in-materio uses evolutionary algorithms to manipulate material substrates for computation. However, in general, modelling the computational processes occurring in such systems is a difficult task and understanding what part of the embodied system is doing the computation is still fairly ill-defined. This chapter discusses the prospects of using Reservoir Computing as a model for in materio computing, introducing new training techniques (taken from Reservoir Computing) that could overcome training difficulties found in the current Evolution-in-Materio technique.

U2 - 10.1007/978-3-319-33924-5_22

DO - 10.1007/978-3-319-33924-5_22

M3 - Chapter

VL - 1

SP - 533

EP - 571

BT - Advances in Unconventional Computing

A2 - Adamatsky, Andrew

PB - Springer

ER -