Universal Criticality in Reservoir Computing Using Asynchronous

IF 0.7 4区数学 Q4 MATHEMATICS, INTERDISCIPLINARY APPLICATIONS

Advances in Complex Systems Pub Date : 2022-03-15 DOI:10.25088/complexsystems.31.1.103

Daisuke Uragami, Y. Gunji

引用次数: 0

Abstract

Elementary cellular automata (ECAs) generate critical spacetime patterns in a few local rules, which are expected to have advantages in reservoir computing (RC). However, previous studies have not revealed the advantages of critical spacetime patterns in RC. In this paper, we focus on the distractor’s length in the time series data for learning and clarify the advantages of the critical spacetime patterns. Furthermore, we propose asynchronously tuned ECAs (AT_ECAs) to generate universally critical spacetime patterns in many local rules. Based on the results achieved in this study, we propose RC based on AT_ECAs. Moreover, we show that the universal criticality of AT_ECAs is effective for learning time series data.

查看原文本刊更多论文

异步油藏计算中的通用临界

初等元胞自动机(ECAs)在一些局部规则下生成临界时空模式，有望在储层计算(RC)中具有优势。然而，以往的研究并没有揭示临界时空模式在RC中的优势。本文以时间序列数据中的干扰物长度为研究对象，阐明了临界时空模式的优势。此外，我们提出了异步调优eca (at_eca)，以在许多局部规则中生成通用临界时空模式。在此基础上，我们提出了基于AT_ECAs的RC。此外，我们还证明了at_eca的普遍临界性对于学习时间序列数据是有效的。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Advances in Complex Systems 综合性期刊-数学跨学科应用

CiteScore

1.40

自引率

0.00%

发文量

121

审稿时长

6-12 weeks

期刊介绍： Advances in Complex Systems aims to provide a unique medium of communication for multidisciplinary approaches, either empirical or theoretical, to the study of complex systems. The latter are seen as systems comprised of multiple interacting components, or agents. Nonlinear feedback processes, stochastic influences, specific conditions for the supply of energy, matter, or information may lead to the emergence of new system qualities on the macroscopic scale that cannot be reduced to the dynamics of the agents. Quantitative approaches to the dynamics of complex systems have to consider a broad range of concepts, from analytical tools, statistical methods and computer simulations to distributed problem solving, learning and adaptation. This is an interdisciplinary enterprise.