Canberk Ekmekci

Ph.D. Student at the University of Rochester, Rochester, NY.

prof_pic.png

Hello, I am Canberk Ekmekci (pronounced Jahn-burk Ehk-mehk-jee), a Ph.D. student in the Department of Electrical and Computer Engineering at the University of Rochester. I received my B.S. degree in Electrical and Electronics Engineering from Koc University, Istanbul, Turkey in 2019. I currently conduct my research under the guidance of Prof. Mujdat Cetin in the Signal, Data, and Imaging Sciences (SDIS) Lab.

My research interests lie primarily in the field of computational imaging, with a particular emphasis on developing and analyzing algorithms for imaging inverse problems. By leveraging techniques from machine learning, sampling, optimization, statistics, and uncertainty quantification, I aim to create trustworthy (robust, reliable, and interpretable) imaging frameworks that integrate data-driven and model-based methodologies in a principled manner. My current research explores topics such as:

  • Bayesian Neural Network-Based Image Reconstruction Methods
  • Calibration Techniques for Probabilistic Image Reconstruction Methods
  • Automated Parameter Tuning for Iterative Image Reconstruction Algorithms
  • Developing Tailored Algorithms for Specific (Imaging) Inverse Problems

Outside of research, I am a passionate Philadelphia 76ers fan and have been closely following the NBA since 2005. I am also a self-declared professional music listener, an avid collector of trading cards, and a casual supporter of the Buffalo Bills. I enjoy hiking and learning about cars as well.

news

Oct 25, 2024 One paper is accepted in Machine Learning and the Physical Sciences Workshop at NeurIPS 2024.
Jun 03, 2024 I started an internship at Argonne National Laboratory, running from June to August 2024.
Nov 13, 2023 One paper is accepted in Geophysical Journal International.
Oct 23, 2023 One paper is accepted in Deep Learning and Inverse Problems Workshop at NeurIPS 2023.
Dec 17, 2022 One paper is accepted in IEEE Transactions on Computational Imaging.