Advanced Search

Show simple item record

dc.contributor.authorKosten, Mehmet Muzaffer
dc.contributor.authorBarut, Murat
dc.contributor.authorAcır, Nurettin
dc.description26th IEEE Signal Processing and Communications Applications Conference (SIU) -- MAY 02-05, 2018 -- Izmir, TURKEYen_US
dc.description.abstractDeep learning-based methods are frequently preferred in many areas in recent years. Another issue, which is as important as deep neural networks applications, is the training of deep neural networks. Although many techniques are proposed in the literature for the training of deep nets, most of these techniques use gradient descent based approaches. In this study, differently from the conventional gradient method, Improved Particle Swam Optimisation (IPSO) algorithm is used for the training of deep neural networks. LeNet-5 network is preferred as network structure and MNIST is utilized as data set. Depending on the number of particles, a performance of up to 96.29% was achieved. In the cases after 20 particles, the average performance was over 90%.en_US
dc.description.sponsorshipIEEE, Huawei, Aselsan, NETAS, IEEE Turkey Sect, IEEE Signal Proc Soc, IEEE Commun Soc, ViSRATEK, Adresgezgini, Rohde & Schwarz, Integrated Syst & Syst Design, Atilim Univ, Havelsan, Izmir Katip Celebi Univen_US
dc.relation.ispartof2018 26Th Signal Processing And Communications Applications Conference (Siu)en_US
dc.relation.ispartofseriesSignal Processing and Communications Applications Conference
dc.subjectdeep learingen_US
dc.subjectdeep netsen_US
dc.subjectdeep networks trainingen_US
dc.titleDeep Neural Network Training with iPSO Algorithmen_US
dc.departmentBTÜ, Mühendislik ve Doğa Bilimleri Fakültesi, Elektrik Elektronik Mühendisliği Bölümüen_US
dc.contributor.institutionauthorAcır, Nurettin
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record