Archives and Documentation Center
Digital Archives

Browsing Bilgisayar Mühendisliği by Subject "Deep learning (Machine learning)"

Browsing Bilgisayar Mühendisliği by Subject "Deep learning (Machine learning)"

Sort by: Order: Results:

  • A common subexpression elimination-based compression method for the constant matrix multipication 
    Bilgili, Emre. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022., 2022)
    The execution time, resource and energy costs of deep learning applications become much more important as their popularity grows. The Constant Matrix Multi plication has been studied for a long time and takes place in deep ...
  • Analysis and regularization of deep generative second order ordinary differential equations 
    Koyuncu, Batuhan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2021., 2021.)
    Deep generative models aim to learn processes that are assumed to generate the data. To this end, deep latent variable models use probabilistic frameworks to learn a joint probability distribution over the data and its ...
  • Attention modeling with temporal shift in sign language recognition 
    Çelimli, Ahmet Faruk. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022., 2022)
    Sign languages (SLs) are the main communication language of deaf people. They are visual languages that establish communication through multiple cues including hand gestures, upper-body movements and facial expressions. ...
  • Data augmentation on chest x-rays for improving pathology classification performance 
    Adıgüzel, Onur. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022., 2022)
    In recent years, deep learning techniques have made great progress. We can see applications of it in many fields such as economics, military, healthcare, and so on. Healthcare, in particular, is one of the most critical ...
  • Deep learning based recommendation system design 
    Şen, Seçil. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2021., 2021.)
    Recommendation systems are software tools that seek to suggest relevant items regarding user preferences. Preference might be any; text to read, product to buy, or anything depending on the industry. Since it’s vastly ...
  • Improving robustness of deep learning systems with fast and customizable adversarial data generation 
    Arıcı, Mehmet Melih. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2021., 2021.)
    Deep Learning (DL) is the force behind the success of solving many complicated tasks in recent years. With the use of DL systems in safety-critical applications, it has become of great importance to make these systems ...
  • Robustness and resilience of deep neural networks 
    Buldu, Abdullah Murat. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022., 2022)
    Deep Neural Networks (DNN) are used extensively to solve challenging problems in computer vision, natural language processing, and speech recognition. However, recent studies such as adversarial attacks show that high ...
  • Unsupervised routing strategies for conditional deep neural networks 
    Meral, Tuna Han Salih. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2022., 2022)
    Deep convolutional neural networks are considered state-of-the- art solutions due to their high classification performance in image classification tasks. The apparent drawback is the amount of computing power required to ...

Search Digital Archive


Browse

My Account