Cargando…

Constructing optimized binary masks for reservoir computing with delay systems

Reservoir computing is a novel bio-inspired computing method, capable of solving complex tasks in a computationally efficient way. It has recently been successfully implemented using delayed feedback systems, allowing to reduce the hardware complexity of brain-inspired computers drastically. In this...

Descripción completa

Detalles Bibliográficos
Autores principales: Appeltant, Lennert, Van der Sande, Guy, Danckaert, Jan, Fischer, Ingo
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Nature Publishing Group 2014
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3887384/
https://www.ncbi.nlm.nih.gov/pubmed/24406849
http://dx.doi.org/10.1038/srep03629
_version_ 1782479009208074240
author Appeltant, Lennert
Van der Sande, Guy
Danckaert, Jan
Fischer, Ingo
author_facet Appeltant, Lennert
Van der Sande, Guy
Danckaert, Jan
Fischer, Ingo
author_sort Appeltant, Lennert
collection PubMed
description Reservoir computing is a novel bio-inspired computing method, capable of solving complex tasks in a computationally efficient way. It has recently been successfully implemented using delayed feedback systems, allowing to reduce the hardware complexity of brain-inspired computers drastically. In this approach, the pre-processing procedure relies on the definition of a temporal mask which serves as a scaled time-mutiplexing of the input. Originally, random masks had been chosen, motivated by the random connectivity in reservoirs. This random generation can sometimes fail. Moreover, for hardware implementations random generation is not ideal due to its complexity and the requirement for trial and error. We outline a procedure to reliably construct an optimal mask pattern in terms of multipurpose performance, derived from the concept of maximum length sequences. Not only does this ensure the creation of the shortest possible mask that leads to maximum variability in the reservoir states for the given reservoir, it also allows for an interpretation of the statistical significance of the provided training samples for the task at hand.
format Online
Article
Text
id pubmed-3887384
institution National Center for Biotechnology Information
language English
publishDate 2014
publisher Nature Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-38873842014-01-10 Constructing optimized binary masks for reservoir computing with delay systems Appeltant, Lennert Van der Sande, Guy Danckaert, Jan Fischer, Ingo Sci Rep Article Reservoir computing is a novel bio-inspired computing method, capable of solving complex tasks in a computationally efficient way. It has recently been successfully implemented using delayed feedback systems, allowing to reduce the hardware complexity of brain-inspired computers drastically. In this approach, the pre-processing procedure relies on the definition of a temporal mask which serves as a scaled time-mutiplexing of the input. Originally, random masks had been chosen, motivated by the random connectivity in reservoirs. This random generation can sometimes fail. Moreover, for hardware implementations random generation is not ideal due to its complexity and the requirement for trial and error. We outline a procedure to reliably construct an optimal mask pattern in terms of multipurpose performance, derived from the concept of maximum length sequences. Not only does this ensure the creation of the shortest possible mask that leads to maximum variability in the reservoir states for the given reservoir, it also allows for an interpretation of the statistical significance of the provided training samples for the task at hand. Nature Publishing Group 2014-01-10 /pmc/articles/PMC3887384/ /pubmed/24406849 http://dx.doi.org/10.1038/srep03629 Text en Copyright © 2014, Macmillan Publishers Limited. All rights reserved http://creativecommons.org/licenses/by-nc-sa/3.0/ This work is licensed under a Creative Commons Attribution-NonCommercial-ShareALike 3.0 Unported License. To view a copy of this license, visit http://creativecommons.org/licenses/by-nc-sa/3.0/
spellingShingle Article
Appeltant, Lennert
Van der Sande, Guy
Danckaert, Jan
Fischer, Ingo
Constructing optimized binary masks for reservoir computing with delay systems
title Constructing optimized binary masks for reservoir computing with delay systems
title_full Constructing optimized binary masks for reservoir computing with delay systems
title_fullStr Constructing optimized binary masks for reservoir computing with delay systems
title_full_unstemmed Constructing optimized binary masks for reservoir computing with delay systems
title_short Constructing optimized binary masks for reservoir computing with delay systems
title_sort constructing optimized binary masks for reservoir computing with delay systems
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3887384/
https://www.ncbi.nlm.nih.gov/pubmed/24406849
http://dx.doi.org/10.1038/srep03629
work_keys_str_mv AT appeltantlennert constructingoptimizedbinarymasksforreservoircomputingwithdelaysystems
AT vandersandeguy constructingoptimizedbinarymasksforreservoircomputingwithdelaysystems
AT danckaertjan constructingoptimizedbinarymasksforreservoircomputingwithdelaysystems
AT fischeringo constructingoptimizedbinarymasksforreservoircomputingwithdelaysystems