An adaptive locally connected neuron model: Focusing neuron

Basit Öğe Kaydı
dc.authorid0000-0002-8649-6013
dc.contributor.authorTek, Faik Borayen_US
dc.date.accessioned2020-10-05T07:31:21Z
dc.date.available2020-10-05T07:31:21Z
dc.date.issued2021-01-02
dc.departmentIşık Üniversitesi, Mühendislik Fakültesi, Bilgisayar Mühendisliği Bölümüen_US
dc.departmentIşık University, Faculty of Engineering, Department of Computer Engineeringen_US
dc.description.abstractThis paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic and well-known image recognition data sets. The results demonstrated that the focusing neurons can move their receptive fields towards more informative inputs. In the simple two-hidden layer networks, the focusing layers outperformed the dense layers in the classification of the 2D spatial data sets. Moreover, the focusing networks performed better than the dense networks even when 70% of the weights were pruned. The tests on convolutional networks revealed that using focusing layers instead of dense layers for the classification of convolutional features may work better in some data sets.en_US
dc.description.sponsorshipThis work was supported by TUBITAK 1001 program (no:118E722), Isik University BAP program (No: 16A202), and NVIDIA hardware donation of a Tesla K40 GPU unit.en_US
dc.description.versionPublisher's Versionen_US
dc.identifier.citationTek, F. B. (2021). An adaptive locally connected neuron model: Focusing neuron. Neurocomputing, 419, 306-321. doi:10.1016/j.neucom.2020.08.008en_US
dc.identifier.doi10.1016/j.neucom.2020.08.008
dc.identifier.endpage321
dc.identifier.issn0925-2312
dc.identifier.issn1872-8286
dc.identifier.scopus2-s2.0-85091648674
dc.identifier.scopusqualityQ1
dc.identifier.startpage306
dc.identifier.urihttps://hdl.handle.net/11729/2541
dc.identifier.urihttp://dx.doi.org/10.1016/j.neucom.2020.08.008
dc.identifier.volume419
dc.identifier.wosWOS:000590168700008
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.indekslendigikaynakScience Citation Index Expanded (SCI-EXPANDED)en_US
dc.institutionauthorTek, Faik Borayen_US
dc.institutionauthorid0000-0002-8649-6013
dc.language.isoenen_US
dc.peerreviewedYesen_US
dc.publicationstatusPublisheden_US
dc.publisherElsevier B.V.en_US
dc.relation.ispartofNeurocomputingen_US
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectAdaptive locally connected neuronen_US
dc.subjectAdaptive receptive fielden_US
dc.subjectAttentionen_US
dc.subjectFocusing neuronen_US
dc.subjectPruningen_US
dc.subjectConvolutionen_US
dc.subjectConvolutional neural networksen_US
dc.subjectFocusingen_US
dc.subjectImage recognitionen_US
dc.subjectNetwork layersen_US
dc.subjectNeuronsen_US
dc.subjectTopologyen_US
dc.subjectArtificial neuronsen_US
dc.subjectConvolutional networksen_US
dc.subjectDense networken_US
dc.subjectHidden layer networksen_US
dc.subjectHidden layersen_US
dc.subjectNeuron networksen_US
dc.subjectReceptive fieldsen_US
dc.subjectSpatial datasetsen_US
dc.subjectClassification (of information)en_US
dc.subjectArticleen_US
dc.subjectAttentionen_US
dc.subjectLearningen_US
dc.subjectNerve cellen_US
dc.subjectReceptive fielden_US
dc.titleAn adaptive locally connected neuron model: Focusing neuronen_US
dc.typeArticleen_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
2541.pdf
Boyut:
3.83 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Publisher's Version
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

MF - Makale Koleksiyonu | Bilgisayar Mühendisliği Bölümü / Department of Computer Engineering
Scopus İndeksli Yayınlar Koleksiyonu
WoS İndeksli Yayınlar Koleksiyonu