• About
  • Policies
  • What is open access
  • Library
  • Contact
Advanced search
      View Item 
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Electrical and Electronics Engineering
      • Dept. of Electrical and Electronics Engineering - Master's degree
      • View Item
      •   BUIR Home
      • University Library
      • Bilkent Theses
      • Theses - Department of Electrical and Electronics Engineering
      • Dept. of Electrical and Electronics Engineering - Master's degree
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Non-uniformly sampled sequential data processing

      Thumbnail
      View / Download
      2.6 Mb
      Author(s)
      Şahin, Safa Onur
      Advisor
      Kozat, Süleyman Serdar
      Date
      2019-09
      Publisher
      Bilkent University
      Language
      English
      Type
      Thesis
      Item Usage Stats
      203
      views
      141
      downloads
      Abstract
      We study classification and regression for variable length sequential data, which is either non-uniformly sampled or contains missing samples. In most sequential data processing studies, one considers data sequence is uniformly sampled and complete, i.e., does not contain missing input values. However, non-uniformly sampled sequences and the missing data problem appear in a wide range of fields such as medical imaging and financial data. To resolve these problems, certain preprocessing techniques, statistical assumptions and imputation methods are usually employed. However, these approaches suffer since the statistical assumptions do not hold in general and the imputation of artificially generated and unrelated inputs deteriorate the model. To mitigate these problems, in chapter 2, we introduce a novel Long Short-Term Memory (LSTM) architecture. In particular, we extend the classical LSTM network with additional time gates, which incorporate the time information as a nonlinear scaling factor on the conventional gates. We also provide forward pass and backward pass update equations for the proposed LSTM architecture. We show that our approach is superior to the classical LSTM architecture, when there is correlation between time samples. In chapter 3, we investigate regression for variable length sequential data containing missing samples and introduce a novel tree architecture based on the Long Short-Term Memory (LSTM) networks. In our architecture, we employ a variable number of LSTM networks, which use only the existing inputs in the sequence, in a tree-like architecture without any statistical assumptions or imputations on the missing data. In particular, we incorporate the missingness information by selecting a subset of these LSTM networks based on presence-pattern of a certain number of previous inputs.
      Keywords
      Long short-term memory
      Recurrent neural networks
      Non-uniform sampling
      Missing data
      Supervised learning
      Permalink
      http://hdl.handle.net/11693/52493
      Collections
      • Dept. of Electrical and Electronics Engineering - Master's degree 597
      Show full item record

      Browse

      All of BUIRCommunities & CollectionsTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartmentsThis CollectionTitlesAuthorsAdvisorsBy Issue DateKeywordsTypeDepartments

      My Account

      LoginRegister

      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 1771
      © Bilkent University - Library IT

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