基于具有时间延迟的光电和光子系统的储层计算的机器学习。

Machine learning based on reservoir computing with time-delayed optoelectronic and photonic systems.

作者信息

Chembo Yanne K

机构信息

Department of Electrical and Computer Engineering, Institute for Research in Electronics and Applied Physics (IREAP), University of Maryland, 8279 Paint Branch Dr., College Park, Maryland 20742, USA.

出版信息

Chaos. 2020 Jan;30(1):013111. doi: 10.1063/1.5120788.

DOI:10.1063/1.5120788

PMID:32013503

Abstract

The concept of reservoir computing emerged from a specific machine learning paradigm characterized by a three-layered architecture (input, reservoir, and output), where only the output layer is trained and optimized for a particular task. In recent years, this approach has been successfully implemented using various hardware platforms based on optoelectronic and photonic systems with time-delayed feedback. In this review, we provide a survey of the latest advances in this field, with some perspectives related to the relationship between reservoir computing, nonlinear dynamics, and network theory.

摘要

储层计算的概念源自一种特定的机器学习范式，其特征在于三层架构（输入层、储层和输出层），其中只有输出层针对特定任务进行训练和优化。近年来，这种方法已通过基于具有时延反馈的光电和光子系统的各种硬件平台成功实现。在本综述中，我们概述了该领域的最新进展，并探讨了一些与储层计算、非线性动力学和网络理论之间关系相关的观点。