Show simple item record

dc.contributor.authorErgen, Tolgaen_US
dc.contributor.authorKozat, Süleyman Serdaren_US
dc.coverage.spatialAntalya, Turkeyen_US
dc.date.accessioned2018-04-12T11:45:11Z
dc.date.available2018-04-12T11:45:11Z
dc.date.issued2017en_US
dc.identifier.urihttp://hdl.handle.net/11693/37600
dc.descriptionDate of Conference: 15-18 May 2017en_US
dc.descriptionConference Name: IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017en_US
dc.description.abstractIn this paper, we study the nonlinear regression problem in a network of nodes and introduce long short term memory (LSTM) based algorithms. In order to learn the parameters of the LSTM architecture in an online manner, we put the LSTM equations into a nonlinear state space form and then introduce our distributed particle filtering (DPF) based training algorithm. Our training algorithm asymptotically achieves the optimal training performance. In our simulations, we illustrate the performance improvement achieved by the introduced algorithm with respect to the conventional methods.en_US
dc.language.isoTurkishen_US
dc.source.titleProceedings of the IEEE 25th Signal Processing and Communications Applications Conference, SIU 2017en_US
dc.relation.isversionofhttp://dx.doi.org/10.1109/SIU.2017.7960220en_US
dc.subjectDistributed particle filteringen_US
dc.subjectLong short term memory networken_US
dc.subjectNonlinear regressionen_US
dc.subjectOnline learningen_US
dc.subjectMonte Carlo methodsen_US
dc.subjectRegression analysisen_US
dc.subjectSignal filtering and predictionen_US
dc.subjectState space methodsen_US
dc.subjectConventional methodsen_US
dc.subjectDistributed particlesen_US
dc.subjectNonlinear regression problemsen_US
dc.subjectNonlinear state spaceen_US
dc.subjectTraining algorithmsen_US
dc.titleOnline distributed nonlinear regression via neural networksen_US
dc.title.alternativeSinir ağları ile çevrimiçi dağıtılmış doğrusal olmayan bağlanımen_US
dc.typeConference Paperen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.identifier.doi10.1109/SIU.2017.7960220en_US
dc.publisherIEEEen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record