Seminerler
-
Computational Approaches to Ideological Bias, Narratives, and Responsible AI
Seminar📅 27.10.2025 — 18:00 👤 Speaker: Dr. Yusuf Mücahit Çetinkaya 📍 Location: Online ⏲ Duration: 60 min. 📝 Abstract: Social media platforms are frequently exploited for manipulation, leading to increased polarization and the spread of narratives with hidden agendas. This talk will present computational approaches to detect, analyze, and… -
System of Systems: Multi-dimensional Classification and Challenges
Seminar📅 22.10.2025 — 14:00 👤 Speaker: Dr. Bedir Tekinerdoğan 📍 Location: BMB5 ⏲ Duration: 60 min. 📝 Abstract: As engineering and technology domains evolve, the concept of a System of Systems (SoS) has emerged as a critical framework for understanding large-scale, heterogeneous integrations of independently managed systems. Despite its… -
Enhancing Efficiency in Large-Scale Search: From Traditional to Neural Retrieval Systems
PhD Thesis📅 04.09.2025 — 17:00 👤 Speaker: ERMAN YAFAY 🎓 Supervisor(s): PROF.DR.ISMAIL SENGOR ALTINGOVDE 📍 Location: A105 ⏲ Duration: 120 min. 📝 Abstract: Efficient retrieval of relevant documents from massive collections remains an essential challenge in Information Retrieval (IR). Modern search engines face immense… -
NATURAL LANGUAGE INTERFACES FOR DATABASES: APPROACHES TO THE PROBLEM OF QUERY GENERATION
PhD Thesis📅 04.09.2025 — 11:00 👤 Speaker: ARIF GORKEM OZER 🎓 Supervisor(s): Prof.Dr. Ismail Hakki Toroslu, Prof. Dr. Pınar Karagoz 📍 Location: A105 ⏲ Duration: 120 min. 📝 Abstract: The number of databases, as well as their size and complexity, is steadily increasing. This trend creates a significant barrier to data access,… -
Enhancing Conversational LLMs through Temporal Contextual Similarity and Formalized Message Retrieval
PhD Thesis📅 03.09.2025 — 13:30 👤 Speaker: EMRE KULAH 🎓 Supervisor(s): ASSOC.PROF.DR.HANDE ALEMDAR 📍 Location: A101 ⏲ Duration: 120 min. 📝 Abstract: Conversational large language models (LLMs) offer powerful generative capabilities, yet remain vulnerable to informal language, hallucinations, and limited contextual awareness.… -
Minimizing Ghosting in High Dynamic Range Images and Videos with Hybrid Approaches and Event Guidance
PhD Thesis📅 03.09.2025 — 13:00 👤 Speaker: KADIR CENK ALPAY 🎓 Supervisor(s): PROF.DR.AHMET OGUZ AKYUZ 📍 Location: A105 ⏲ Duration: 120 min. 📝 Abstract: The increased interest in consumer-grade high dynamic range (HDR) images and videos in recent years has caused a proliferation of HDR deghosting algorithms. Despite numerous… -
Ballistic identification of firearms with deep learning
PhD Thesis📅 01.09.2025 — 14:00 👤 Speaker: EDANUR DEMIR MERAL 🎓 Supervisor(s): PROF.DR.A.OGUZ AKYUZ 📍 Location: A101 ⏲ Duration: 120 min. 📝 Abstract: Ballistic examination systems rely on analyzing surface markings on cartridge cases to identify firearms used in criminal cases. However, current systems using traditional image… -
A ONE-CLASS CLASSIFICATION MODEL USING MULTI-LEVEL FEATURES FOR ANOMALY DETECTION IN INDUSTRIAL IMAGES
MSc Thesis📅 01.09.2025 — 13:30 👤 Speaker: YUSUF SOYDAN 🎓 Supervisor(s): ASSOC.PROF.DR.SEYDA ERTEKIN 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: In industrial environments, visual inspection done by workers is time-consuming and prone to errors. To overcome these problems, deep learning methods were proposed as a promising… -
PRIVACY-PRESERVING ANOMALY DETECTION FOR SMART ENERGY MANAGEMENT
PhD Thesis📅 01.09.2025 — 11:00 👤 Speaker: MANOLYA ATALAY 🎓 Supervisor(s): ASSOC.PROF.DR.PELIN ANGIN ULKUER 📍 Location: A105 ⏲ Duration: 120 min. 📝 Abstract: The widespread deployment of smart meters in modern energy grids introduces not only unprecedented opportunities for high-frequency analytics, but also acute privacy and… -
ADAPTIVE PARAMETER OPTIMIZATION FOR REINFORCEMENT LEARNING-BASED SPARK JOB SCHEDULING
MSc Thesis📅 29.08.2025 — 10:00 👤 Speaker: BURAK SEN 🎓 Supervisor(s): PROF.DR.MURAT MANGUOGLU 📍 Location: A105 ⏲ Duration: 90 min. 📝 Abstract: This study presents an investigation on adaptive parameter optimization techniques for Reinforcement Learning-based Apache Spark job scheduling. Traditional Rein- forcement Learning-based…