Saved in:
Bibliographic Details
Main Authors: Chiba, Hayato, Taniguchi, Koichi, Sumi, Takuma
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.16172
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909854766989312
author Chiba, Hayato
Taniguchi, Koichi
Sumi, Takuma
author_facet Chiba, Hayato
Taniguchi, Koichi
Sumi, Takuma
contents Reservoir computing aims to achieve high-performance and low-cost machine learning with a dynamical system as a reservoir. However, in general, there are almost no theoretical guidelines for its high-performance or optimality. Therefore, this paper aims to propose the new concept {\it the edge of bifurcation} for designing a high-performance reservoir, and provide a mathematical justification for it. This concept is a generalization of the famous criterion {\it the edge of chaos}. For this purpose, this paper focuses on the reservoir computing with the Kuramoto model and theoretically reveals its approximation ability. The main result provides an explicit expression of the dynamics of the Kuramoto reservoir by using the order parameters. Thus, the output of the reservoir computing is expressed as a linear combination of the order parameters. As a corollary, sufficient conditions on hyperparameters are obtained so that the set of the order parameters gives the complete basis of the Lebesgue space. This implies that the Kuramoto reservoir has a universal approximation property. Furthermore, the edge of bifurcation is also discussed from the viewpoint of its approximation ability. It is numerically demonstrated by prediction tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16172
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reservoir computing with the Kuramoto model
Chiba, Hayato
Taniguchi, Koichi
Sumi, Takuma
Dynamical Systems
Reservoir computing aims to achieve high-performance and low-cost machine learning with a dynamical system as a reservoir. However, in general, there are almost no theoretical guidelines for its high-performance or optimality. Therefore, this paper aims to propose the new concept {\it the edge of bifurcation} for designing a high-performance reservoir, and provide a mathematical justification for it. This concept is a generalization of the famous criterion {\it the edge of chaos}. For this purpose, this paper focuses on the reservoir computing with the Kuramoto model and theoretically reveals its approximation ability. The main result provides an explicit expression of the dynamics of the Kuramoto reservoir by using the order parameters. Thus, the output of the reservoir computing is expressed as a linear combination of the order parameters. As a corollary, sufficient conditions on hyperparameters are obtained so that the set of the order parameters gives the complete basis of the Lebesgue space. This implies that the Kuramoto reservoir has a universal approximation property. Furthermore, the edge of bifurcation is also discussed from the viewpoint of its approximation ability. It is numerically demonstrated by prediction tasks.
title Reservoir computing with the Kuramoto model
topic Dynamical Systems
url https://arxiv.org/abs/2407.16172