Melih Kandemir


Campusvej 55, 5230,

Odense, Denmark


Melih is an Associate Professor of Machine Learning at the University of Southern Denmark, Department of Mathematics and Computer Science (IMADA). Melih earned his PhD degree from Aalto University in 2013 under the supervision of Prof. Samuel Kaski. He worked as a postdoctoral researcher at Heidelberg University with Prof. Fred Hamprecht and as an assistant professor at Ozyegin University in Istanbul, Turkey. Prior to joining SDU, Melih was leading a research group at Bosch Center for Artificial Intelligence.

Melih is the founder and PI of the SDU Adaptive Intelligence (ADIN) Lab, which pursues basic research on Bayesian inference and stochastic process modeling with deep neural nets with application to reinforcement learning and continual learning. Melih is proud to be an ELLIS Member, the society of the top artificial intelligence researchers in the Europe.

Melih is fascinated by both popular and technical aspects of natural sciences, especially physics and biology. His leisure time goes to thinking wishfully about their applications to the development of environment-friendly technologies.

Melih is in love with his wife Fatos and his daughter Sehnaz.

Selected Publications

  1. NeurIPS
    Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures
    H. Flynn, D. Reeb, M. Kandemir, and 1 more author
    In Neural Information Processing Systems 2023
  2. T-PAMI
    PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison
    H. Flynn, D. Reeb, M. Kandemir, and 1 more author
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2023
  3. ICLR
    Evidential Turing Processes
    M. Kandemir, A. Akgül, M. Haussmann, and 1 more author
    In International Conference on Learning Representations 2022
  4. T-PAMI
    A Deterministic Approximation to Neural SDEs
    A. Look, M. Kandemir, B. Rakitsch, and 1 more author
    IEEE Transactions on Pattern Analysis and Machine Intelligence 2022
  5. IJCAI
    Deep Active Learning with Adaptive Acquisition
    M. Haußmann, F.A. Hamprecht, and M. Kandemir
    In International Joint Conference on Artificial Intelligence 2019
  6. NeurIPS
    Evidential Deep Learning to Quantify Classification Uncertainty
    M. Sensoy, L. Kaplan, and M. Kandemir
    In Neural Information Processing Systems 2018