Analysis of reservoir computing focusing on the spectrum of bistable delayed dynamical systems. Issue 2 (21st December 2018)

• Record Type: Journal Article
• Authors: Kinoshita, Ikuhide; Akao, Akihiko; Shirasaka, Sho; Kotani, Kiyoshi; Jimbo, Yasuhiko
• Is Part Of: Electronics and communications in Japan. Volume 102:Issue 2(2019)
• Page Start: 15
• Page End: 20
• Publication Date: 2018-12-21
• Subjects: bistable systems -- delayed dynamical systems -- reservoir computing; Electronics -- Periodicals; Telecommunication -- Periodicals; 621.6805
• DOI: 10.1002/ecj.12142
• Languages: English
• ISSNs: 1942-9533

Abstract

Abstract: Reservoir computing (RC) is a machine‐learning paradigm that is capable to process empirical time series data. This paradigm is based on a neural network with a fixed hidden layer having a high‐dimensional state space, called a reservoir. Reservoirs including time delays are considered to be good candidates for practical applications because they make hardware realization of the high‐dimensional reservoirs simple. Performance of the well‐trained RCs depends both on dynamical properties of attractors of the reservoirs and tasks they solve. Therefore, in the conventional monostable RCs, there arise task‐wise optimization problems of the reservoirs, which have been solved based on trial and error approaches. In this study, we analyzed the relationship between the dynamical properties of the time‐delay reservoir and the performance in terms of the spectra of the delayed dynamical systems, which might facilitate the development of the unified systematic optimization techniques for the time‐delay reservoirs. In addition, we propose a novel RC framework that performs well on distinct tasks without the task‐wise optimization using bistable reservoir dynamics, which can reduce complicated hardware management of the reservoirs.