Insight into delay based reservoir computing via eigenvalue analysis

Author:

Köster FelixORCID,Yanchuk SerhiyORCID,Lüdge KathyORCID

Abstract

Abstract In this paper we give a profound insight into the computation capability of delay based reservoir computing via an eigenvalue analysis. We concentrate on the task-independent memory capacity to quantify the reservoir performance and compare these with the eigenvalue spectrum of the dynamical system. We show that these two quantities are deeply connected, and thus the reservoir computing performance is predictable by analysing the small signal response of the reservoir. Our results suggest that any dynamical system used as a reservoir can be analysed in this way. We apply our method exemplarily to a photonic laser system with feedback and compare the numerically computed recall capabilities with the eigenvalue spectrum. Optimal performance is found for a system with the eigenvalues having real parts close to zero and off-resonant imaginary parts.

Funder

Deutsche Forschungsgemeinschaft

Publisher

IOP Publishing

Subject

Electrical and Electronic Engineering,Atomic and Molecular Physics, and Optics,Electronic, Optical and Magnetic Materials

Reference67 articles.

1. The ‘echo state’ approach to analysing and training recurrent neural networks;Jaeger,2001

2. Real-time computing without stable states: a new framework for neural computation based on perturbations;Maass;Neural Comput.,2002

3. Reservoir computing universality with stochastic inputs;Gonon;IEEE Trans. Neural Netw. Learn. Syst.,2020

4. Pattern Recognition in a Bucket

5. Online training of an opto-electronic reservoir computer applied to real-time channel equalization;Antonik;IEEE Trans. Neural Netw. Learn. Syst.,2016

Cited by 19 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3