• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      •   BUIR Home
      • Scholarly Publications
      • Faculty of Engineering
      • Department of Electrical and Electronics Engineering
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Yeni bir ögrenme algoritması: SinAdaMax

      Thumbnail
      View / Download
      225.6 Kb
      Author(s)
      Çatalbaş, Burak
      Morgül, Ömer
      Date
      2019-04
      Source Title
      27th Signal Processing and Communications Applications Conference (SIU), 2019
      Publisher
      IEEE
      Pages
      1 - 4
      Language
      Turkish
      Type
      Conference Paper
      Item Usage Stats
      162
      views
      111
      downloads
      Abstract
      Yapay Sinir Ağları yaklaşık 21. yüzyılın ilk 10 yılından sonra başlayan ‘Derin Ögrenme’ çağından beri makine öğrenmesi alanını büyük ölçüde etkilemektedir. Sinir ağı eğitimi başarısı ağ parametrelerini modifiye eden eniyileyicilere oldukça bağlıdır ve eniyileyicinin uygulandığı ağların eğitimdeki başarısını önemli oranda etkiler. Bu çalışmada, farklı eniyileyiciler duygu analizi, görsel sınıflandırması gibi farklı problemlerde kullanılmış ve başarılarının gösterilmesi için kıyaslanmıştır. Bu araştırmada önceden önerdigimiz yeni eniyileyici SinAdaMax’in başarısını göstermek için, tekrarlı ve evrişimsel ağ tipleri ile farklı veri setlerinde, yaygın olarak bilinen diğer eniyileyiciler de denenmiştir.
       
      Artificial Neural Networks are clearly influencing the field of machine learning since the age of the `Deep Learning', roughly starting after the first 10 years of the 21st century. The neural network training success highly depends on the optimizers which modify the network weights, and these learning algorithms affect the success of the training of the networks significantly. In this work, different optimizers are employed in different problems like sentiment analysis and image classification for comparing and figuring out the successful ones. To show the success of the new optimizer SinAdaMax we proposed previously, recurrent and convolutional neural networks on different datasets are used with other well-known learning algorithms in this research.
      Keywords
      Artificial neural networks
      Optimizer
      CIFAR-10
      IMDb large movie review dataset
      Permalink
      http://hdl.handle.net/11693/52956
      Published Version (Please cite this version)
      https://doi.org/10.1109/SIU.2019.8806259
      Collections
      • Department of Electrical and Electronics Engineering 4011
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCoursesThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsCourses

      My Account

      Login

      Statistics

      View Usage StatisticsView Google Analytics Statistics

      Bilkent University

      If you have trouble accessing this page and need to request an alternate format, contact the site administrator. Phone: (312) 290 2976
      © Bilkent University - Library IT

      Contact Us | Send Feedback | Off-Campus Access | Admin | Privacy