By the same authors

From the same journal

From the same journal

Reservoir computing quality: connectivity and topology

Research output: Contribution to journalArticlepeer-review

Standard

Reservoir computing quality : connectivity and topology. / Dale, Matthew; O'Keefe, Simon; Sebald, Angelika; Stepney, Susan; Trefzer, Martin Albrecht.

In: Natural Computing, 15.12.2020.

Research output: Contribution to journalArticlepeer-review

Harvard

Dale, M, O'Keefe, S, Sebald, A, Stepney, S & Trefzer, MA 2020, 'Reservoir computing quality: connectivity and topology', Natural Computing. https://doi.org/10.1007/s11047-020-09823-1

APA

Dale, M., O'Keefe, S., Sebald, A., Stepney, S., & Trefzer, M. A. (2020). Reservoir computing quality: connectivity and topology. Natural Computing. https://doi.org/10.1007/s11047-020-09823-1

Vancouver

Dale M, O'Keefe S, Sebald A, Stepney S, Trefzer MA. Reservoir computing quality: connectivity and topology. Natural Computing. 2020 Dec 15. https://doi.org/10.1007/s11047-020-09823-1

Author

Dale, Matthew ; O'Keefe, Simon ; Sebald, Angelika ; Stepney, Susan ; Trefzer, Martin Albrecht. / Reservoir computing quality : connectivity and topology. In: Natural Computing. 2020.

Bibtex - Download

@article{3d1b2e54bbed447ab3cf404644f465f5,
title = "Reservoir computing quality: connectivity and topology",
abstract = "We explore the effect of connectivity and topology on the dynamical behaviour of Reservoir Computers. At present, considerable effort is taken to design and hand-craft physical reservoir computers. Both structure and physical complexity are often pivotal to task performance, however, assessing their overall importance is challenging. Using a recently developed framework, we evaluate and compare the dynamical freedom (referring to quality) of neural network structures, as an analogy for physical systems. The results quantify how structure affects the behavioural range of networks. It demonstrates how high quality reached by more complex structures is often also achievable in simpler structures with greater network size. Alternatively, quality is often improved in smaller networks by adding greater connection complexity. This work demonstrates the benefits of using dynamical behaviour to assess the quality of computing substrates, rather than evaluation through benchmark tasks that often provide a narrow and biased insight into the computing quality of physical systems.",
author = "Matthew Dale and Simon O'Keefe and Angelika Sebald and Susan Stepney and Trefzer, {Martin Albrecht}",
note = "{\textcopyright} The Author(s) 2020 ",
year = "2020",
month = dec,
day = "15",
doi = "10.1007/s11047-020-09823-1",
language = "English",
journal = "Natural Computing",
issn = "1567-7818",
publisher = "Springer Netherlands",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Reservoir computing quality

T2 - connectivity and topology

AU - Dale, Matthew

AU - O'Keefe, Simon

AU - Sebald, Angelika

AU - Stepney, Susan

AU - Trefzer, Martin Albrecht

N1 - © The Author(s) 2020

PY - 2020/12/15

Y1 - 2020/12/15

N2 - We explore the effect of connectivity and topology on the dynamical behaviour of Reservoir Computers. At present, considerable effort is taken to design and hand-craft physical reservoir computers. Both structure and physical complexity are often pivotal to task performance, however, assessing their overall importance is challenging. Using a recently developed framework, we evaluate and compare the dynamical freedom (referring to quality) of neural network structures, as an analogy for physical systems. The results quantify how structure affects the behavioural range of networks. It demonstrates how high quality reached by more complex structures is often also achievable in simpler structures with greater network size. Alternatively, quality is often improved in smaller networks by adding greater connection complexity. This work demonstrates the benefits of using dynamical behaviour to assess the quality of computing substrates, rather than evaluation through benchmark tasks that often provide a narrow and biased insight into the computing quality of physical systems.

AB - We explore the effect of connectivity and topology on the dynamical behaviour of Reservoir Computers. At present, considerable effort is taken to design and hand-craft physical reservoir computers. Both structure and physical complexity are often pivotal to task performance, however, assessing their overall importance is challenging. Using a recently developed framework, we evaluate and compare the dynamical freedom (referring to quality) of neural network structures, as an analogy for physical systems. The results quantify how structure affects the behavioural range of networks. It demonstrates how high quality reached by more complex structures is often also achievable in simpler structures with greater network size. Alternatively, quality is often improved in smaller networks by adding greater connection complexity. This work demonstrates the benefits of using dynamical behaviour to assess the quality of computing substrates, rather than evaluation through benchmark tasks that often provide a narrow and biased insight into the computing quality of physical systems.

U2 - 10.1007/s11047-020-09823-1

DO - 10.1007/s11047-020-09823-1

M3 - Article

JO - Natural Computing

JF - Natural Computing

SN - 1567-7818

ER -