Theory and applications of multifunctional reservoir computers

Simple item page
dc.contributor.advisorAmann, Andreas
dc.contributor.advisorexternalTsachouridis, Vassilios A.
dc.contributor.authorFlynn, Andrewen
dc.contributor.funderIrish Research Councilen
dc.date.accessioned2023-09-14T10:41:02Z
dc.date.available2023-09-14T10:41:02Z
dc.date.issued2023
dc.date.submitted2023
dc.description.abstractIn the pursuit of developing artificially intelligent systems there is much to be gained from dually integrating further physiological features of biological neural networks and knowledge of dynamical systems into machine learning environments. In this Thesis such a two-armed approach is employed in order to translate 'multifunctionality' from biological to artificial neural networks via the reservoir computing machine learning paradigm. Multifunctionality describes the ability of a single neural network that exploits a form of multistability to perform a multitude of mutually exclusive tasks. The dynamics of multifunctional RCs are assessed across several tasks and from this many new application areas are explored which include, data-driven modelling of multistability, generating chaotic itinerancy, and reconstructing dynamical transitions present in the epileptic brain.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationFlynn, A. 2023. Theory and applications of multifunctional reservoir computers. PhD Thesis, University College Cork.
dc.identifier.endpage240
dc.identifier.urihttps://hdl.handle.net/10468/14980
dc.language.isoenen
dc.publisherUniversity College Corken
dc.relation.projectIrish Research Council (Grant EPSPG/2017/301)
dc.rights© 2023, Andrew Flynn.
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectNonlinear dynamics
dc.subjectReservoir computing
dc.subjectMachine learning
dc.subjectMultifunctionality
dc.subjectComputational neuroscience
dc.titleTheory and applications of multifunctional reservoir computersen
dc.typeDoctoral thesisen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD - Doctor of Philosophyen
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
FlynnA_PhD2023.pdf
Size:
16.67 MB
Format:
Adobe Portable Document Format
Description:
Full Text E-thesis (wrong cover page)
Thumbnail Image
Name:
Submission for Examination Form
Size:
418.27 KB
Format:
Adobe Portable Document Format
Thumbnail Image
Name:
FlynnA_PhD2023.pdf
Size:
16.67 MB
Format:
Adobe Portable Document Format
Description:
Full text E-thesis
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
5.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Theses
College of Science, Engineering and Food Science - Doctoral Theses
Mathematical Sciences - Doctoral Theses