Browsing by Author "Yılmaz, Selim Fırat"

Now showing items 1-5 of 5

    • Achieving online regression performance of LSTMs with simple RNNs 

      Vural, Nuri Mert; İlhan, Fatih; Yılmaz, Selim Fırat; Ergüt, S.; Kozat, Süleyman Serdar (Institute of Electrical and Electronics Engineers, 2021-06-17)
      Recurrent neural networks (RNNs) are widely used for online regression due to their ability to generalize nonlinear temporal dependencies. As an RNN model, long short-term memory networks (LSTMs) are commonly preferred in ...

    • Eskrim sporunun Türkiye’ye girişi ve Türkiye'deki tarihi 

      Gür, Barış; Şimşekli, Faruk; Vural, Fatma Zehra; Yılmaz, Selim Fırat; Çapa, Sinan (Bilkent University, 2017)

    • Multi-label sentiment analysis on 100 languages with dynamic weighting for label imbalance 

      Yılmaz, Selim Fırat; Kaynak, Ergün Batuhan; Koç, Aykut; Dibeklioğlu, Hamdi; Kozat, Süleyman Serdar (Institute of Electrical and Electronics Engineers, 2021-07-19)
      We investigate cross-lingual sentiment analysis, which has attracted significant attention due to its applications in various areas including market research, politics, and social sciences. In particular, we introduce a ...

    • Multimodal analysis of personality traits on videos of self-presentation and induced behavior 

      Giritlioğlu, Dersu; Mandira, Burak; Yılmaz, Selim Fırat; Ertenli, C. U.; Akgür, Berhan Faruk; Kınıklıoğlu, Merve; Kurt, Aslı Gül; Mutlu, E.; Dibeklioğlu, Hamdi (Springer, 2020)
      Personality analysis is an important area of research in several fields, including psychology, psychiatry, and neuroscience. With the recent dramatic improvements in machine learning, it has also become a popular research ...

    • Unsupervised anomaly detection via deep metric learning with end-to-end optimization 

      Yılmaz, Selim Fırat (Bilkent University, 2021-07)
      We investigate unsupervised anomaly detection for high-dimensional data and introduce a deep metric learning (DML) based framework. In particular, we learn a distance metric through a deep neural network. Through this ...