Fen Bilimleri Enstitüsü: Recent submissions

  • Constant-space, constant-randomness verifiers with arbitrarily small strong error 
    Gezer, Mehmet Utkan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2020., 2020.)
    We study the capabilities of probabilistic finite-state machines that act as verifiers for certificates of language membership for input strings, in the regime where the verifiers are restricted to toss some fixed nonzero ...
  • Adversarial one-shot voice conversion using disentangled representations 
    Yeşilkanat, Ali. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2020., 2020.)
    In this thesis, a new adversarial one-shot voice conversion (VC) method is introduced by enhancing one of the latest variational autoencoder based one-shot VC methods. The proposed method utilizes acoustic features as ...
  • Learning temporal sensorimotor distributions of complex robotic manipulation skills with conditional neural processes 
    Şeker, Muhammet Yunus. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2020., 2020.)
    This thesis proposes a new framework, namely Conditional Neural Movement Primitives (CNMPs) that is a learning from demonstration framework designed as a robotic movement learning and generation system built on top of a ...
  • Neural Sign Language Translation by learning tokenization 
    Orbay, Alptekin. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2020., 2020.)
    In this thesis, we propose a multitask learning based method to improve Neural Sign Language Translation (NSLT) consisting of two parts, a tokenization layer and Neural Machine Translation (NMT). The tokenization part ...
  • Score level multi cue fusion for sign language recognition 
    Gökçe, Çağrı. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2020., 2020.)
    In this thesis, we propose a Score-Level Multi Cue Fusion approach that improves the sign language recognition performance of the three dimensional convolutional neural networks. Sign Language is the communication language ...
  • Spatially varying single image deblurring using cyclegans 
    Ünlü, Gizem Esra. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    In this thesis, we propose a novel method that learns to deblur hand images in the presence of spatially-varying object motion blur and unpaired blurry/sharp training pairs. While some success has been achieved in image ...
  • Detection of antibiotic resistance in bacteria via machine learning approaches 
    Erkut, Hamdi. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Tuberculosis, which is sometimes referred as white plague, is one of the most dangerous diseases caused by bacteria in our era. The species causing the sickness is in the family of Mycobacteriaceae and called mycobacterium ...
  • Intrinsic and extrinsic evaluation of word embedding models 
    Yeşiltaş, Gökçe. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    In natural language processing tasks, representing a word is an important issue. After Bengio et al. introduced a simple neural network language model that learns word vector representations in 2003, representing words in ...
  • Parallel tetrahedral mesh refinement 
    Balman, Mehmet. (Thesis (M.S.)-Bogazici University. Institute for Graduate Studies in Science and Engineering, 2006., 2006.)
    The Adaptive Mesh Refinement is one of the main techniques used for the solutionof Partial Differential Equations. Since 3-dimensional structures are more complex,there are few refinement methods especially for parallel ...
  • A multi-tasking executive 
    Yılmazer, Sedat. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 1984., 1984.)
    This thesis describes the design and implementation of a real-time multi-tasking priority-driven executive, FOX. The name stands for "a East ObJect oriented executive. FOX permits the micro-computer user to enjoy the ...
  • Recommendation extension to the iterated prisoner's dilemma game 
    Çınar, Zeynep Büşra. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Optimism, pessimism, and realism are human dispositions that are used in everyday life to describe the typical behavior of a certain personality type. In this study, we investigate the effects of these dispositions on trust ...
  • Hit song prediction using feature-based machine learning 
    Çalışkol, Anıl Orhan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Music industry is making big investments every year to produce hit songs. The increasing number of songs available through digital platforms can enable the development of learning models for predicting hit songs and ...
  • Extracting protein-ligand interactions from the biomedical literature using deep learning approaches 
    Yüksel, Atakan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Protein-ligand interactions play crucial roles in living organisms, thus they attract many researchers from various disciplines. There are protein-ligand interaction databases that provide information to researchers in a ...
  • Emotional impact of movies 
    Karslıoğlu İman, Nihan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Video emotion estimation has been an active area of research in recent decades. This study area is crucial for personalized content delivery, video recommendation, video summarization, and inappropriate scene censorship. ...
  • 3D human pose estimation from multi-view RGB images 
    Temiz, Hüseyin. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Recovery of a 3D human pose from cameras has been the subject of intensive research in the last decade. Algorithms that can estimate the 3D pose from a single image have been developed. At the same time, many camera ...
  • Multilingual identification of verbal multiword expressions using bidirectional long short-term memory based architectures 
    Berk, Gözde. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Verbal multiword expression (VMWE) identi cation is a challenging task for many natural language processing studies. In this study, sequence tagging approach accompanied with stochastic models and variants of IOB tagging ...
  • Fauly tolerance in the data plane of software-defined networks 
    Yamansavaşçılar, Barış. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Failures in networks result in service disruptions which may cause deteriorated Quality of Service for the end users. Since SDN is becoming the mainstream paradigm for networks, especially for data centers, correct ...
  • Identification of verbal multiword expressions using deep learning architectures and representation learning methods 
    Erden, Berna. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    Understanding multiword expressions (MWEs) plays an instrumental role in Natural Language Processing applications such as parsing and machine translation. MWE identi cation is a task that automatically detects and classi ...
  • Improving the performance of LoRaWAN IoT system 
    Yapar, Gökçer. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    One of the technologies developed in LPWAN according to the IoT concept is the LoRaWAN protocol. This protocol works together with LoRa modulation. So far, studies on this protocol included only uplink communication. ...
  • Multivariate product demand forecasting with neural networks 
    Şahin, Çağatay. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2019., 2019.)
    In retail, there are plenty of use cases that would benefit from predicting the future amount of product sales. Those use cases include cash ow management, campaign execution and inventory planning, all of which are the ...

Search Digital Archive


Browse

My Account