Basit öğe kaydını göster

dc.contributor.advisorKuru, Selahattinen_US
dc.contributor.authorDalkılıç, Hikmeten_US
dc.contributor.otherIşık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programıen_US
dc.date.accessioned2016-05-31T13:31:23Z
dc.date.available2016-05-31T13:31:23Z
dc.date.issued2005-06
dc.identifier.citationDalkılıç, H. (2005). Spline based neural networks. İstanbul: Işık Üniversitesi Fen Bilimleri Enstitüsü.en_US
dc.identifier.urihttps://hdl.handle.net/11729/892
dc.descriptionText in English ; Abstract: English and Turkishen_US
dc.descriptionIncludes bibliographical references (leaves 70-71)en_US
dc.descriptionX, 72 leavesen_US
dc.description.abstractIn this thesis, we applied the Catmull-Rom splines and B-splines to the neural networks models, which are Multi Layer Perceptrons, Elman Networks, and Locally Recurrent Neural Networks, as adaptive activation functions. We derived the learning algorithms for the five new neural network models, which we proposed. This new models are called 2Multi Layer Perceptrons with Adaptive B- Spline Activation Function3, 2Elman Networks with Adaptive Catmull-Rom Spline Activation Function3, 2Elman Networks with Adaptive B- Spline Activation Function3, 2Locally Recurrent Neural Networks with Adaptive Catmull-Rom Spline Activation Function3, 2Locally Recurrent Neural Networks with Adaptive B- Spline Activation Function3. We measure the performance of these networks on the xor problem and compare the performance of them for this problem. To simulate the networks and to compare their performances we developed a web-based neural network simulator written in PHP 4 called SBNN.en_US
dc.description.abstractBu tez ile, Catmull-Rom spline fonksiyonları ve B-spline fonksiyonları uyarlanabilir aktivasyon fonksiyonları olarak, yapay sinir ağı modelleri olan Çok Katmanlı Ağlara,Elman ağlarına ve Yerel Geri Beslemeli ağlara uygulandı. Bu uygulamalardan oluşturduğumuz 5 yeni yapay sinir ağı modeli için öğrenme algoritmalarının çıkarımları yapıldı. Bu yeni modeller sırasıyla 2Uyarlanabilir Catmull-Rom Spline Aktivasyon Fonksiyonlu Çok Katmanlı Ağlar3, 2Uyarlanabilir B-Spline Aktivasyon Fonksiyonlu Çok Katmanlı Ağlar3 , 2Uyarlanabilir Catmull-Rom Spline Aktivasyon Fonksiyonlu Elman Ağları3, 2Uyarlanabilir B-Spline Aktivasyon Fonksiyonlu Elman Ağları3, 2Uyarlanabilir Catmull-Rom Spline Aktivasyon Fonksiyonlu Yerel Geri Beslemeli ağlar3, ve son olarak 2Uyarlanabilir B- Spline Aktivasyon Fonksiyonlu Yerel Geri Beslemeli ağlar3 diye adlandırılır. Ağların performansı xor problemi kullanılarak ölçüldü ve sonuçları birbirleriyle karşılaştırıldı. Yapay sinir ağlarını oluşturulması ve performanslarının ölçülmesi için SBNN adında PHP 4 programlama dilin ile yazılmış web tabanlı bir yapay sinir ağı similatörü geliştirildi.en_US
dc.description.tableofcontentsINTRODUCTIONen_US
dc.description.tableofcontentsSPLINE FUNCTIONSen_US
dc.description.tableofcontentsSpline Specificationen_US
dc.description.tableofcontentsSpline Function’s Mathematical Descriptionen_US
dc.description.tableofcontentsMULTI LAYER PERCEPTRONen_US
dc.description.tableofcontentsMulti Layer Perceptron with Sigmoid Activation Functionsen_US
dc.description.tableofcontentsThe Structure of Multi Layer Perceptronen_US
dc.description.tableofcontentsDelta Learning Ruleen_US
dc.description.tableofcontentsMulti Layer Perceptron with Adaptive Catmull-Rom Spline Activation Functionsen_US
dc.description.tableofcontentsGradient-Based Learning for Multi layer Perceptron with Adaptive Spline Activation Functionen_US
dc.description.tableofcontentsMulti Layer Perceptron with Adaptive Catmull-Rom Spline Activation Functionsen_US
dc.description.tableofcontentsELMAN NEURAL NETWORKSen_US
dc.description.tableofcontentsElman Networks with Sigmoid Activation Functionen_US
dc.description.tableofcontentsElman Networks With Adaptive Catmull-Rom Spline Activation Functionsen_US
dc.description.tableofcontentsElman Networks With Adaptive B-Spline Activation Functionsen_US
dc.description.tableofcontentsLOCALLY RECURRENT NEURAL NETWORKSen_US
dc.description.tableofcontentsLocally Recurrent Neural Networks with Sigmoid Activation Functionsen_US
dc.description.tableofcontentsLocally Recurrent Neural Networks with Adaptive Catmull-Rom Spline Activation Functionsen_US
dc.description.tableofcontentsLocally Recurrent Neural Networks with Adaptive B-Spline Activation Functionsen_US
dc.description.tableofcontentsPERFORMANS OFTHE NETWORKSen_US
dc.description.tableofcontentsComparison of the Multi Layer Perceptronen_US
dc.description.tableofcontentsComparison of the sigmoid activation functions and the B-spline activation function for MLPen_US
dc.description.tableofcontentsComparison of the Catmull-Rom spline activation functions and the B-spline activation functions for MLPen_US
dc.description.tableofcontentsComparison of the Elman Networksen_US
dc.description.tableofcontentsComparison of the sigmoid activation functions and the B-spline activation function for Elman Networksen_US
dc.description.tableofcontentsComparison of the Catmull-Rom spline activation functions and the B-spline activation functions for Elman Networksen_US
dc.description.tableofcontentsComparison of the Catmull-Rom spline activation functions and the sigmoid activation functions for Elman Networksen_US
dc.description.tableofcontentsComparison of the Locally Recurrent Neural Networksen_US
dc.description.tableofcontentsComparison of the sigmoid activation functions and the B-spline activation function for Locally Recurrent Neural Networksen_US
dc.description.tableofcontentsComparison of the Catmull-Rom spline activation functions and the sigmoid activation functions for Locally Recurrent Neural Networksen_US
dc.description.tableofcontentsComparison of execution time of all modelen_US
dc.description.tableofcontentsSPLINE BASED NEURAL NETWORK SIMULATOR (SBNN)en_US
dc.description.tableofcontentsSoftware Specification of SBNNen_US
dc.description.tableofcontentsThe aim of this Softwareen_US
dc.description.tableofcontentsThe Menu of the SBNNen_US
dc.description.tableofcontentsTraining a networken_US
dc.description.tableofcontentsTraining a networken_US
dc.description.tableofcontentsRunning and deleting a networken_US
dc.description.tableofcontentsComparing the Network Performanceen_US
dc.description.tableofcontentsComparing the Execution time performanceen_US
dc.description.tableofcontentsCONCLUSION AND RECOMMENDATIONS FOR FUTURE WORen_US
dc.description.tableofcontentsCD containing Thesis text and software codeen_US
dc.language.isoengen_US
dc.publisherIşık Üniversitesien_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subjectAdaptive activation functionsen_US
dc.subjectAdaptive catmull-rom spline activation functionsen_US
dc.subjectAdoptive B- spline activation functionsen_US
dc.subjectSBNNen_US
dc.subjectSpline activation functionsen_US
dc.subjectSpline networksen_US
dc.subjectSpline ağlarıen_US
dc.subjectSpline aktivasyon fonksiyonlarıen_US
dc.subjectUyarlanabilir aktivasyon fonksiyonlarıen_US
dc.subjectUyarlanabilir B-spline aktivasyon fonksiyonlarıen_US
dc.subjectUyarlanabilir catmull-rom spline aktivasyon fonksiyonlarıen_US
dc.subject.lccQA76.87 .D35 2005
dc.subject.lcshNeural networks (Computer science)en_US
dc.subject.lcshSpline theory -- Data processing.en_US
dc.subject.lcshComputer-aided design.en_US
dc.titleSpline based neural networksen_US
dc.title.alternativeSpline tabanlı yapay sinir ağlarıen_US
dc.typemasterThesisen_US
dc.contributor.departmentIşık Üniversitesi, Fen Bilimleri Enstitüsü, Bilgisayar Mühendisliği Yüksek Lisans Programıen_US
dc.relation.publicationcategoryTezen_US
dc.contributor.institutionauthorDalkılıç, Hikmeten_US


Bu öğenin dosyaları:

Thumbnail

Bu öğe aşağıdaki koleksiyon(lar)da görünmektedir.

Basit öğe kaydını göster

info:eu-repo/semantics/openAccess
Aksi belirtilmediği sürece bu öğenin lisansı: info:eu-repo/semantics/openAccess