Guiding principle of reservoir computing based on “small-world” network
Abstract Reservoir computing is a computational framework of recurrent neural networks and is gaining attentions because of its drastically simplified training process. For a given task to solve, however, the methodology has not yet been established how to construct an optimal reservoir. While, “sma...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2022-10-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-022-21235-y |
_version_ | 1811226622159749120 |
---|---|
author | Ken-ichi Kitayama |
author_facet | Ken-ichi Kitayama |
author_sort | Ken-ichi Kitayama |
collection | DOAJ |
description | Abstract Reservoir computing is a computational framework of recurrent neural networks and is gaining attentions because of its drastically simplified training process. For a given task to solve, however, the methodology has not yet been established how to construct an optimal reservoir. While, “small-world” network has been known to represent networks in real-world such as biological systems and social community. This network is categorized amongst those that are completely regular and totally disordered, and it is characterized by highly-clustered nodes with a short path length. This study aims at providing a guiding principle of systematic synthesis of desired reservoirs by taking advantage of controllable parameters of the small-world network. We will validate the methodology using two different types of benchmark tests—classification task and prediction task. |
first_indexed | 2024-04-12T09:28:13Z |
format | Article |
id | doaj.art-a4ecab8b6a2647fdbbede6e39229b3dc |
institution | Directory Open Access Journal |
issn | 2045-2322 |
language | English |
last_indexed | 2024-04-12T09:28:13Z |
publishDate | 2022-10-01 |
publisher | Nature Portfolio |
record_format | Article |
series | Scientific Reports |
spelling | doaj.art-a4ecab8b6a2647fdbbede6e39229b3dc2022-12-22T03:38:26ZengNature PortfolioScientific Reports2045-23222022-10-0112111010.1038/s41598-022-21235-yGuiding principle of reservoir computing based on “small-world” networkKen-ichi Kitayama0National Institute of Information and Communications TechnologyAbstract Reservoir computing is a computational framework of recurrent neural networks and is gaining attentions because of its drastically simplified training process. For a given task to solve, however, the methodology has not yet been established how to construct an optimal reservoir. While, “small-world” network has been known to represent networks in real-world such as biological systems and social community. This network is categorized amongst those that are completely regular and totally disordered, and it is characterized by highly-clustered nodes with a short path length. This study aims at providing a guiding principle of systematic synthesis of desired reservoirs by taking advantage of controllable parameters of the small-world network. We will validate the methodology using two different types of benchmark tests—classification task and prediction task.https://doi.org/10.1038/s41598-022-21235-y |
spellingShingle | Ken-ichi Kitayama Guiding principle of reservoir computing based on “small-world” network Scientific Reports |
title | Guiding principle of reservoir computing based on “small-world” network |
title_full | Guiding principle of reservoir computing based on “small-world” network |
title_fullStr | Guiding principle of reservoir computing based on “small-world” network |
title_full_unstemmed | Guiding principle of reservoir computing based on “small-world” network |
title_short | Guiding principle of reservoir computing based on “small-world” network |
title_sort | guiding principle of reservoir computing based on small world network |
url | https://doi.org/10.1038/s41598-022-21235-y |
work_keys_str_mv | AT kenichikitayama guidingprincipleofreservoircomputingbasedonsmallworldnetwork |