Abdullah Akgül

AbdullahAkgül.JPG

Abdullah was born in Karaman in July 1997. He lived the first two years of his life in Erzincan and turned back to his hometown which is Karaman. He was interested in math and computer since he was a child.

Abdullah spent his free time with computers and the amazing world of math. He graduated from “Karaman Fen Lisesi” in 2015.

After high school, he started to study computer engineering at ITU. Since he has a lot of interest in robotics and electronics, he began studying Control and Automation Engineering as a second major in 2018. However, as a choice, he decided to continue his education in computer engineering and dropped the second major. He was studying in the field of Artificial Intelligence, Reinforcement Learning, and Robotics. The graduation project, titled “Robotic Manipulation with Tools in Kitchen Environment”, for the computer engineering degree was in these fields.

After his bachelor’s degree, he started master’s in ITU. During his master’s, he worked mainly on uncertainty, calibration, and continual learning. He graduated with a thesis titled “Memory-based Approaches to Problems in Probabilistic Modeling” in 2022.

Now, Abdullah is a PhD student at the University of Southern Denmark.

selected publications

  1. NeurIPS
    Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
    A. Akgül, M. Haussmann, and M. Kandemir
    In Neural Information Processing Systems 2024
  2. L4DC
    Continual Learning of Multi-modal Dynamics with External Memory
    Abdullah Akgül, G. Unal, and M. Kandemir
    In Proceedings of The 6th Annual Learning for Dynamics and Control Conference 2024
  3. ICLR
    Evidential Turing Processes
    M. Kandemir, Abdullah Akgül, M. Haussmann, and 1 more author
    In International Conference on Learning Representations 2022
  4. FL-NeurIPS
    How to Combine Variational Bayesian Networks in Federated Learning
    A. Ozer, K.B. Buldu, Abdullah Akgül, and 1 more author
    In Workshop on Federated Learning: Recent Advances and New Challenges (in Conjunction with NeurIPS 2022) 2022