Reservoir Computing Benchmarks: a tutorial review and critique

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wringe, Chester, Trefzer, Martin, Stepney, Susan
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909515724619776
author Wringe, Chester
Trefzer, Martin
Stepney, Susan
author_facet Wringe, Chester
Trefzer, Martin
Stepney, Susan
contents Reservoir Computing is an Unconventional Computation model to perform computation on various different substrates, such as recurrent neural networks or physical materials. The method takes a 'black-box' approach, training only the outputs of the system it is built on. As such, evaluating the computational capacity of these systems can be challenging. We review and critique the evaluation methods used in the field of reservoir computing. We introduce a categorisation of benchmark tasks. We review multiple examples of benchmarks from the literature as applied to reservoir computing, and note their strengths and shortcomings. We suggest ways in which benchmarks and their uses may be improved to the benefit of the reservoir computing community.
format Preprint
id arxiv_https___arxiv_org_abs_2405_06561
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reservoir Computing Benchmarks: a tutorial review and critique
Wringe, Chester
Trefzer, Martin
Stepney, Susan
Emerging Technologies
Machine Learning
Neural and Evolutionary Computing
Reservoir Computing is an Unconventional Computation model to perform computation on various different substrates, such as recurrent neural networks or physical materials. The method takes a 'black-box' approach, training only the outputs of the system it is built on. As such, evaluating the computational capacity of these systems can be challenging. We review and critique the evaluation methods used in the field of reservoir computing. We introduce a categorisation of benchmark tasks. We review multiple examples of benchmarks from the literature as applied to reservoir computing, and note their strengths and shortcomings. We suggest ways in which benchmarks and their uses may be improved to the benefit of the reservoir computing community.
title Reservoir Computing Benchmarks: a tutorial review and critique
topic Emerging Technologies
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2405.06561