Dale, Matthew, Dewhirst, Jack Daniel, O'Keefe, Simon Edward Marius orcid.org/0000-0001-5957-2474 et al. (3 more authors) (2019) The role of structure and complexity on Reservoir Computing quality. In: UCNC 2019, Tokyo, Japan, June 2019, 03-07 Jun 2019.
Abstract
We explore the effect of structure and connection complexity on the dynamical behaviour of Reservoir Computers (RC). 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 proposed 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 range of behaviours exhibited by these networks. It highlights that 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 abstract behaviour representation, rather than evaluation through benchmark tasks, to assess the quality of computing substrates, as the latter typically has biases, and often provides little insight into the complete computing quality of physical systems.
Metadata
Item Type: | Conference or Workshop Item |
---|---|
Authors/Creators: |
|
Keywords: | Complexity,Echo state networks,Reservoir computing,Structure,Unconventional computing |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) The University of York > Faculty of Sciences (York) > Chemistry (York) The University of York > Faculty of Sciences (York) > Electronic Engineering (York) |
Depositing User: | Pure (York) |
Date Deposited: | 14 Jun 2019 13:40 |
Last Modified: | 23 Jan 2025 00:43 |
Published Version: | https://doi.org/10.1007/978-3-030-19311-9_6 |
Status: | Published |
Refereed: | Yes |
Identification Number: | 10.1007/978-3-030-19311-9_6 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:147383 |