Reservoir Computing in materio with LEDs

Research output: Contribution to conferencePaper

Standard

Reservoir Computing in materio with LEDs. / Dale, Matthew Nicholas; Miller, Julian Francis; Stepney, Susan; Trefzer, Martin Albrecht.

2017. Paper presented at International Conference on Unconventional Computation and Natural Computation, Fayetteville, United States.

Research output: Contribution to conferencePaper

Harvard

Dale, MN, Miller, JF, Stepney, S & Trefzer, MA 2017, 'Reservoir Computing in materio with LEDs' Paper presented at International Conference on Unconventional Computation and Natural Computation, Fayetteville, United States, 5/06/17 - 9/06/17, .

APA

Dale, M. N., Miller, J. F., Stepney, S., & Trefzer, M. A. (2017). Reservoir Computing in materio with LEDs. Paper presented at International Conference on Unconventional Computation and Natural Computation, Fayetteville, United States.

Vancouver

Dale MN, Miller JF, Stepney S, Trefzer MA. Reservoir Computing in materio with LEDs. 2017. Paper presented at International Conference on Unconventional Computation and Natural Computation, Fayetteville, United States.

Author

Dale, Matthew Nicholas ; Miller, Julian Francis ; Stepney, Susan ; Trefzer, Martin Albrecht. / Reservoir Computing in materio with LEDs. Paper presented at International Conference on Unconventional Computation and Natural Computation, Fayetteville, United States.

Bibtex - Download

@conference{ee0851d5c11a4b03bfbbb2e475a8e800,
title = "Reservoir Computing in materio with LEDs",
abstract = "We have shown that the Reservoir Computing framework transfers to complex substrates, and that performance can increase significantly when we control and manipulate input-output mappings and external perturbation through computer-controlled evolution. We have implemented a new example of the hardware-based reservoir methodology. We have two new types of reservoirs based on Light Emitting Diodes (LEDs) and resistors. Results show that unconstrained computer-controlled evolution can exploit the net effect of variations in components (resistors and diodes) to form a single reservoir competitive to previous findings.",
keywords = "evolution in materio, Unconventional computing, evolvable hardware, natural computation, Carbon Nanotubes (CNTs), led diode",
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",

}

RIS (suitable for import to EndNote) - Download

TY - CONF

T1 - Reservoir Computing in materio with LEDs

AU - Dale, Matthew Nicholas

AU - Miller, Julian Francis

AU - Stepney, Susan

AU - Trefzer, Martin Albrecht

PY - 2017

Y1 - 2017

N2 - We have shown that the Reservoir Computing framework transfers to complex substrates, and that performance can increase significantly when we control and manipulate input-output mappings and external perturbation through computer-controlled evolution. We have implemented a new example of the hardware-based reservoir methodology. We have two new types of reservoirs based on Light Emitting Diodes (LEDs) and resistors. Results show that unconstrained computer-controlled evolution can exploit the net effect of variations in components (resistors and diodes) to form a single reservoir competitive to previous findings.

AB - We have shown that the Reservoir Computing framework transfers to complex substrates, and that performance can increase significantly when we control and manipulate input-output mappings and external perturbation through computer-controlled evolution. We have implemented a new example of the hardware-based reservoir methodology. We have two new types of reservoirs based on Light Emitting Diodes (LEDs) and resistors. Results show that unconstrained computer-controlled evolution can exploit the net effect of variations in components (resistors and diodes) to form a single reservoir competitive to previous findings.

KW - evolution in materio

KW - Unconventional computing

KW - evolvable hardware

KW - natural computation

KW - Carbon Nanotubes (CNTs)

KW - led diode

M3 - Paper

ER -