Recurrent neural networks based online learning algorithms for distributed systems

Simple item page
dc.contributor.authorErgen, Tolgaen_US
dc.contributor.authorŞahin, S. Onuren_US
dc.contributor.authorKozat, S. Serdaren_US
dc.coverage.spatialIzmir, Turkeyen_US
dc.date.accessioned2019-02-21T16:05:15Zen_US
dc.date.available2019-02-21T16:05:15Zen_US
dc.date.issued2018en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 2-5 May 2018en_US
dc.description.abstractIn this paper, we investigate online parameter learning for Long Short Term Memory (LSTM) architectures in distributed networks. Here, we first introduce an LSTM based structure for regression. Then, we provide the equations of this structure in a state space form for each node in our network. Using this form, we then learn the parameters via our Distributed Particle Filtering based (DPF) training method. Our training method asymptotically converges to the optimal parameter set provided that we satisfy certain trivial requirements. While achieving this performance, our training method only causes a computational load that is similar to the efficient first order gradient based training methods. Through real life experiments, we show substantial performance gains compared to the conventional methods.en_US
dc.description.provenanceMade available in DSpace on 2019-02-21T16:05:15Z (GMT). No. of bitstreams: 1 Bilkent-research-paper.pdf: 222869 bytes, checksum: 842af2b9bd649e7f548593affdbafbb3 (MD5) Previous issue date: 2018en
dc.identifier.doi10.1109/SIU.2018.8404806en_US
dc.identifier.isbn9781538615010en_US
dc.identifier.urihttp://hdl.handle.net/11693/50241en_US
dc.language.isoTurkishen_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.isversionofhttps://doi.org/10.1109/SIU.2018.8404806en_US
dc.source.title2018 26th Signal Processing and Communications Applications Conference (SIU)en_US
dc.subjectDistributed systemsen_US
dc.subjectLong short term memory networksen_US
dc.subjectOnline trainingen_US
dc.subjectSequential regressionen_US
dc.titleRecurrent neural networks based online learning algorithms for distributed systemsen_US
dc.title.alternativeDağıtılmış sistemler için tekrarlanan sinir ağları merkezli çevrimiçi öğrenim algoritmalarıen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Recurrent_neural_networks_based_online_learning_algorithms_for_distributed_systems.pdf
Size:
842.31 KB
Format:
Adobe Portable Document Format
Description:
Full printable version
Download

Collections

Scholarly Publications - Electrical and Electronics Engineering