Affiliation:
1. US Naval Research Laboratory 1 , Washington, DC 20375, USA
2. Department of Mechanical Engineering, University of New Mexico 2 , Albuquerque, New Mexico 87131, USA
Abstract
Reservoir computing, a recurrent neural network paradigm in which only the output layer is trained, has demonstrated remarkable performance on tasks such as prediction and control of nonlinear systems. Recently, it was demonstrated that adding time-shifts to the signals generated by a reservoir can provide large improvements in performance accuracy. In this work, we present a technique to choose the time-shifts by maximizing the rank of the reservoir matrix using a rank-revealing QR algorithm. This technique, which is not task dependent, does not require a model of the system and, therefore, is directly applicable to analog hardware reservoir computers. We demonstrate our time-shift selection technique on two types of reservoir computer: an optoelectronic reservoir computer and the traditional recurrent network with a t a n h activation function. We find that our technique provides improved accuracy over random time-shift selection in essentially all cases.
Funder
Naval Research Laboratory Basic Research Program
Office of the Secretary of Defense
Subject
Applied Mathematics,General Physics and Astronomy,Mathematical Physics,Statistical and Nonlinear Physics
Cited by
2 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
1. Synchronizing chaos using reservoir computing;Chaos: An Interdisciplinary Journal of Nonlinear Science;2023-10-01
2. Detecting disturbances in network-coupled dynamical systems with machine learning;Chaos: An Interdisciplinary Journal of Nonlinear Science;2023-10-01