Extendible Hardware Platform for Reservoir Computing in materio

Matthew Nicholas Dale; Julian Francis Miller; Susan Stepney; Martin Albrecht Trefzer

Extendible Hardware Platform for Reservoir Computing in materio

Matthew Nicholas Dale, Julian Francis Miller, Susan Stepney, Martin Albrecht Trefzer

Research output: Contribution to conference › Paper › peer-review

Abstract

We have shown that the theoretical framework of Reservoir Computing (RC) can be applied to in materio computing as a computational layer able to extract exploitable information from physical substrates. However, a physical performance limitation of our current system is the number of interfacing electrodes to the material. We have designed and built a new hardware platform that in- creases the previous 12 electrode system to a 64 multi-purpose electrode system. This extra flexibility allows improved performance.

Original language	English
Publication status	Published - 2017
Event	International Conference on Unconventional Computation and Natural Computation - Arkansas, Fayetteville, United States Duration: 5 Jun 2017 → 9 Jun 2017 Conference number: 16 https://ucnc2017.csce.uark.edu

Conference

Conference	International Conference on Unconventional Computation and Natural Computation
Abbreviated title	UCNC
Country/Territory	United States
City	Fayetteville
Period	5/06/17 → 9/06/17
Internet address	https://ucnc2017.csce.uark.edu

Keywords

evolution in materio
unconventional computing
natural computation
Carbon Nanotubes (CNTs)
evolvable hardware

Access to Document

https://www-users.cs.york.ac.uk/susan/bib/ss/nonstd/ucnc2017-platform.pdf

Cite this

@conference{99eed31f3df941e9b555d71470e58871,

title = "Extendible Hardware Platform for Reservoir Computing in materio",

abstract = "We have shown that the theoretical framework of Reservoir Computing (RC) can be applied to in materio computing as a computational layer able to extract exploitable information from physical substrates. However, a physical performance limitation of our current system is the number of interfacing electrodes to the material. We have designed and built a new hardware platform that in- creases the previous 12 electrode system to a 64 multi-purpose electrode system. This extra flexibility allows improved performance.",

keywords = "evolution in materio, unconventional computing, natural computation, Carbon Nanotubes (CNTs), evolvable hardware",

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

year = "2017",

language = "English",

note = "International Conference on Unconventional Computation and Natural Computation, UCNC ; Conference date: 05-06-2017 Through 09-06-2017",

url = "https://ucnc2017.csce.uark.edu",

}

TY - CONF

T1 - Extendible Hardware Platform for Reservoir Computing in materio

AU - Dale, Matthew Nicholas

AU - Miller, Julian Francis

AU - Stepney, Susan

AU - Trefzer, Martin Albrecht

N1 - Conference code: 16

PY - 2017

Y1 - 2017

N2 - We have shown that the theoretical framework of Reservoir Computing (RC) can be applied to in materio computing as a computational layer able to extract exploitable information from physical substrates. However, a physical performance limitation of our current system is the number of interfacing electrodes to the material. We have designed and built a new hardware platform that in- creases the previous 12 electrode system to a 64 multi-purpose electrode system. This extra flexibility allows improved performance.

AB - We have shown that the theoretical framework of Reservoir Computing (RC) can be applied to in materio computing as a computational layer able to extract exploitable information from physical substrates. However, a physical performance limitation of our current system is the number of interfacing electrodes to the material. We have designed and built a new hardware platform that in- creases the previous 12 electrode system to a 64 multi-purpose electrode system. This extra flexibility allows improved performance.

KW - evolution in materio

KW - unconventional computing

KW - natural computation

KW - Carbon Nanotubes (CNTs)

KW - evolvable hardware

M3 - Paper

T2 - International Conference on Unconventional Computation and Natural Computation

Y2 - 5 June 2017 through 9 June 2017

ER -