Browsing Master's Theses by Author "Aydoğan, Reyhan"
Now showing items 1-16 of 16
-
An actor-critic reinforcement learning approach for bilateral negotiation
Designing an effective and intelligent bidding strategy is one of the most compelling research challenges in automated negotiation, where software agents negotiate with each other to find a mutual agreement when there is ... -
Adapting bilateral networks to monocular depth estimation for real-time inference
Monocular Depth Estimation (MDE) is a fundamental computer vision application area for many industry-related advances. Due to its deployment needs, the inference time of the depth estimation algorithm also plays a crucial ... -
Agent based negotiation for incentive driven privacy preserving information sharing
Razeghi, Yousef (2019-08-20)While customizing their services, companies usually use their users’ data. According to the new regularization, it is required to get the permission of their users to be able to store and share their users’ private data. ... -
Associative and frequentist opponent modeling approaches in automated bilateral negotiations
This thesis mainly focuses on the problem of learning opponent's preferences during the negotiation in bilateral automated negotiation in which agents negotiate with each other to reach an agreement. Accordingly, it addresses ... -
Black-box test case selection by relating code changes with previously fixed defects
Software continuously changes to address new requirements and to fix defects. Regression testing is performed to ensure that the applied changes do not adversely affect existing functionality. The increasing number of test ... -
Clothing image retrieval with triplet capsule networks
Kınlı, Osman Furkan (2019-08-19)Clothing image retrieval has become more important after some major developments in Computer Science and the emergence of e-commerce. Recent studies generally attack this problem by using Convolutional Neural Networks ... -
Effect of embodiment in human-agent negotiations
With the current advancement in artificial intelligence, intelligent systems interacting with humans are becoming more prevalent in our lives. One of the challenges is building socially intelligent agents who can effectively ... -
Explorations on inverse reinforcement learning for the analysis of motor control and cognitive decision making mechanisms of the brain
Reinforcement Learning is a framework for generating optimal policies given a task and a reward/punishment structure. Likewise, Inverse Reinforcement Learning, as the name suggests, is used for recovering the reasoning ... -
Fusion of subjective opinions through behavior estimation
Aycı, Gönül (2016-01)Information is significantly important in almost all decision-making process. A decision- maker agent collects information from diverse sources. Thus, it should correctly fuse opinions, which are shared from different ... -
High-level representations through unconstrained sensorimotor learning
Living organisms, in particular mammals are adept at learning complex tasks that may require basic planning such as tool use and manipulation. This ability is manifested by the central nervous system; in particular by the ... -
Image denoising using deep convolutional autoencoders
Çetinkaya, Ekrem (2019-08-19)Image denoising is one of the fundamental problems in image processing eld since it is required by many computer vision applications. Various approaches have been used in image denoising throughout the years from spatial ... -
Multi-lingual depression-level assessment from conversational speech using acoustic and text features
Özkanca, Yasin Serdar (2018-12-19)Depression is a common mental health problem around the world with a large burden on economies, well-being, hence productivity, of individuals. Early diagnosis and detection of depression can aid treatment, but diagnosis ... -
Multi-scale binary similarity a local binary pattern variant for face recognition
Tavlı, Ahmet (2018-08)Face recognition problem were studied for more than four-decade, and many descriptors and neural network architectures have been proposed since then. The aim is simple, extract features from the same subjects for training ... -
Negotiation-based decentralized conflict resolution in multi-agent path finding
This thesis addresses the problem of Multi-Agent Path Finding problem where multiple agents aim to reach their destination in a grid world without any colli sion. It aims to provide a solution achieving good trade-off ... -
Risk-calibrated evidential classifiers
Saleki, Maryam (2020-01-17)In some applications, intelligent agents rely on classifiers in order to make their decisions and accuracy of their predictions may play a significant role in performing their tasks successfully. Although deep neural ... -
Solving 3-SAT problem using a quantum-simulated absorbing classical random walk approach
Quantum computing offers novel approaches for solving computationally hard problems. In this thesis, we present a quantum algorithm based on the quantum simulation of Schöning's algorithm for solving the 3-SAT problem. We ...
Share this page