Exploring the limits of multifunctionality across different reservoir computers

Simple item page
dc.contributor.authorFlynn, Andrew
dc.contributor.authorHeilmann, Oliver
dc.contributor.authorKöglmayr, Daniel
dc.contributor.authorTsachouridis, Vassilios A.
dc.contributor.authorRäth, Christoph
dc.contributor.authorAmann, Andreas
dc.contributor.funderIrish Research Councilen
dc.date.accessioned2022-12-07T12:15:26Z
dc.date.available2022-12-07T12:15:26Z
dc.date.issued2022-09-30
dc.date.updated2022-12-07T09:59:14Z
dc.description.abstractMultifunctional neural networks are capable of performing more than one task without changing any network connections. In this paper we explore the performance of a continuous-time, leaky-integrator, and next-generation 'reservoir computer' (RC), when trained on tasks which test the limits of multifunctionality. In the first task we train each RC to reconstruct a coexistence of chaotic attractors from different dynamical systems. By moving the data describing these attractors closer together, we find that the extent to which each RC can reconstruct both attractors diminishes as they begin to overlap in state space. In order to provide a greater understanding of this inhibiting effect, in the second task we train each RC to reconstruct a coexistence of two circular orbits which differ only in the direction of rotation. We examine the critical effects that certain parameters can have in each RC to achieve multifunctionality in this extreme case of completely overlapping training data.en
dc.description.sponsorshipIrish Research Council (Enterprise Partnership Scheme Grant No. EPSPG/2017/301)en
dc.description.statusPeer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationFlynn, A., Heilmann, O., Köglmayr, D., Tsachouridis, V. A., Räth, C. and Amann, A. (2022) 'Exploring the limits of multifunctionality across different reservoir computers', 2022 International Joint Conference on Neural Networks (IJCNN), Padua, Italy, 18-23 July. doi: 10.1109/IJCNN55064.2022.9892203en
dc.identifier.doi10.1109/IJCNN55064.2022.9892203en
dc.identifier.eissn2161-4407
dc.identifier.endpage8en
dc.identifier.isbn978-1-7281-8671-9
dc.identifier.isbn978-1-6654-9526-4
dc.identifier.issn2161-4393
dc.identifier.startpage1en
dc.identifier.urihttps://hdl.handle.net/10468/13907
dc.language.isoenen
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en
dc.relation.ispartof2022 International Joint Conference on Neural Networks (IJCNN)
dc.rights© 2022, IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en
dc.subjectFloquet analysisen
dc.subjectMultifunctionalityen
dc.subjectReservoir Computingen
dc.titleExploring the limits of multifunctionality across different reservoir computersen
dc.typeConference itemen
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Exploring_the_limits_of_multifunctionality_across_different_reservoir_computers.pdf
Size:
1.34 MB
Format:
Adobe Portable Document Format
Description:
Accepted Version
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
2.71 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Mathematical Sciences - Conference Items