Please use this identifier to cite or link to this item:
Publication type: Article in scientific journal
Type of review: Peer review (publication)
Title: Abstract reservoir computing
Authors: Senn, Christoph Walter
Kumazawa, Itsuo
et. al: No
DOI: 10.3390/ai3010012
Published in: AI
Volume(Issue): 3
Issue: 1
Page(s): 194
Pages to: 210
Issue Date: 10-Mar-2022
Publisher / Ed. Institution: MDPI
ISSN: 2673-2688
Language: English
Subjects: Reservoir computing; Echo state network; Recurrent neural network; Simulation; Robustness
Subject (DDC): 006: Special computer methods
Abstract: Noise of any kind can be an issue when translating results from simulations to the real world. We suddenly have to deal with building tolerances, faulty sensors, or just noisy sensor readings. This is especially evident in systems with many free parameters, such as the ones used in physical reservoir computing. By abstracting away these kinds of noise sources using intervals, we derive a regularized training regime for reservoir computing using sets of possible reservoir states. Numerical simulations are used to show the effectiveness of our approach against different sources of errors that can appear in real-world scenarios and compare them with standard approaches. Our results support the application of interval arithmetics to improve the robustness of mass-spring networks trained in simulations.
Fulltext version: Published version
License (according to publishing contract): CC BY 4.0: Attribution 4.0 International
Departement: School of Engineering
Organisational Unit: Institute of Applied Mathematics and Physics (IAMP)
Appears in collections:Publikationen School of Engineering

Files in This Item:
File Description SizeFormat 
2022_Senn-Kumazawa_Abstract-Reservoir-Computing.pdf5.2 MBAdobe PDFThumbnail

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.