Model-size reduction for reservoir computing by concatenating internal states through time

Yusuke Sakemi, Kai Morino, Timothée Leleu, Kazuyuki Aihara

Research output: Contribution to journalArticlepeer-review

Abstract

Reservoir computing (RC) is a machine learning algorithm that can learn complex time series from data very rapidly based on the use of high-dimensional dynamical systems, such as random networks of neurons, called “reservoirs.” To implement RC in edge computing, it is highly important to reduce the amount of computational resources that RC requires. In this study, we propose methods that reduce the size of the reservoir by inputting the past or drifting states of the reservoir to the output layer at the current time step. To elucidate the mechanism of model-size reduction, the proposed methods are analyzed based on information processing capacity proposed by Dambre et al. (Sci Rep 2:514, 2012). In addition, we evaluate the effectiveness of the proposed methods on time-series prediction tasks: the generalized Hénon-map and NARMA. On these tasks, we found that the proposed methods were able to reduce the size of the reservoir up to one tenth without a substantial increase in regression error.

Original languageEnglish
Article number21794
JournalScientific reports
Volume10
Issue number1
DOIs
Publication statusPublished - Dec 2020

All Science Journal Classification (ASJC) codes

  • General

Fingerprint Dive into the research topics of 'Model-size reduction for reservoir computing by concatenating internal states through time'. Together they form a unique fingerprint.

Cite this