{"id":{"repo_id":"cork","oai_identifier":"oai:cora.ucc.ie:10468/16503"},"canonical_url":"https://search.dev.ndltd.org/etd/cork/oai:cora.ucc.ie:10468/16503","repository":{"repo_id":"cork","name":"University College Cork","base_url":"https://cora.ucc.ie/server/oai/request"},"display":{"title":"Dynamics of adaptive recurrent neural networks","abstract":"In this thesis a simple, phenomenological model of a neural network with plasticity is presented in the form of a slow-fast adaptive dynamical recurrent neural network. The plasticity rule is chosen from the class of Hebbian learning rules, in which the synaptic connection between two neurons evolves continuously as a function of their correlation in the recent past. Initially an analysis of networks of two neurons is presented, which exhibit relaxation oscillations in which one neuron switches between an ’off’ state, where it takes a negative value, and an ’on’ state, where it takes a positive value, while the other neuron stays in one on/off state. Then, by means of an example with a nine neuron network, the system is shown to exhibit both stable frequency cluster synchronization and transient frequency cluster synchronization.","abstract_html":"In this thesis a simple, phenomenological model of a neural network with plasticity is presented in the form of a slow-fast adaptive dynamical recurrent neural network. The plasticity rule is chosen from the class of Hebbian learning rules, in which the synaptic connection between two neurons evolves continuously as a function of their correlation in the recent past. Initially an analysis of networks of two neurons is presented, which exhibit relaxation oscillations in which one neuron switches between an ’off’ state, where it takes a negative value, and an ’on’ state, where it takes a positive value, while the other neuron stays in one on/off state. Then, by means of an example with a nine neuron network, the system is shown to exhibit both stable frequency cluster synchronization and transient frequency cluster synchronization.","abstract_has_math":false,"creators":["Fox, David"],"institution":"University College Cork","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Amann, Andreas","Keane, Andrew"],"committee_chairs":[],"committee_members":[],"year":2023,"date_issued":"2023","date_published":"2023","updated_at":"2026-07-24T01:47:55Z","subjects":["Nonlinear dynamics","Bifurcation theory","Dynamical systems","Computaional neuroscience","Neural networks","Recurrent neural networks","Synchronization","Slow-fast systems","Multiple timescales","Adaptive dynamical networks"],"languages":["en"],"rights":["© 2023, David Fox."],"rights_urls":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10468/16503","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Amann, Andreas","Keane, Andrew"]},{"key":"dc:creator","label":"Author","values":["Fox, David"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-10-03T14:19:29Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2024-10-03T14:19:29Z"]},{"key":"dc:date.issued","label":"Date","values":["2023"]},{"key":"dc:publisher","label":"Institution","values":["University College Cork"]},{"key":"dc:type","label":"Dc Type","values":["Masters thesis (Research)"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["Masters"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["MSc - Master of Science"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Nonlinear dynamics","Bifurcation theory","Dynamical systems","Computaional neuroscience","Neural networks","Recurrent neural networks","Synchronization","Slow-fast systems","Multiple timescales","Adaptive dynamical networks"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["© 2023, David Fox."]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://creativecommons.org/licenses/by-nc-nd/4.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10468/16503"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["In this thesis a simple, phenomenological model of a neural network with plasticity is presented in the form of a slow-fast adaptive dynamical recurrent neural network. The plasticity rule is chosen from the class of Hebbian learning rules, in which the synaptic connection between two neurons evolves continuously as a function of their correlation in the recent past. Initially an analysis of networks of two neurons is presented, which exhibit relaxation oscillations in which one neuron switches between an ’off’ state, where it takes a negative value, and an ’on’ state, where it takes a positive value, while the other neuron stays in one on/off state. Then, by means of an example with a nine neuron network, the system is shown to exhibit both stable frequency cluster synchronization and transient frequency cluster synchronization."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Dynamics of adaptive recurrent neural networks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Amann, Andreas","Keane, Andrew"],"dc:creator":["Fox, David"],"dc:date.accessioned":["2024-10-03T14:19:29Z"],"dc:date.available":["2024-10-03T14:19:29Z"],"dc:date.issued":["2023"],"dc:description.abstract":["In this thesis a simple, phenomenological model of a neural network with plasticity is presented in the form of a slow-fast adaptive dynamical recurrent neural network. The plasticity rule is chosen from the class of Hebbian learning rules, in which the synaptic connection between two neurons evolves continuously as a function of their correlation in the recent past. Initially an analysis of networks of two neurons is presented, which exhibit relaxation oscillations in which one neuron switches between an ’off’ state, where it takes a negative value, and an ’on’ state, where it takes a positive value, while the other neuron stays in one on/off state. Then, by means of an example with a nine neuron network, the system is shown to exhibit both stable frequency cluster synchronization and transient frequency cluster synchronization."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10468/16503"],"dc:language.iso":["en"],"dc:publisher":["University College Cork"],"dc:rights":["© 2023, David Fox."],"dc:rights.uri":["https://creativecommons.org/licenses/by-nc-nd/4.0/"],"dc:subject":["Nonlinear dynamics","Bifurcation theory","Dynamical systems","Computaional neuroscience","Neural networks","Recurrent neural networks","Synchronization","Slow-fast systems","Multiple timescales","Adaptive dynamical networks"],"dc:title":["Dynamics of adaptive recurrent neural networks"],"dc:type":["Masters thesis (Research)"],"dc:type.qualificationlevel":["Masters"],"dc:type.qualificationname":["MSc - Master of Science"]},"updated_at":"2026-07-24T01:47:55Z"}