Berken Utku Demirel

prof_pic.gif

ETH Hauptgebäude Terrace

I am currently a third-year Ph.D. student in the Department of Computer Science at ETH Zurich, supervised by Professor Christian Holz. My research focuses on learning theory and signal processing, aiming to design robust machine learning algorithms with minimal supervision by developing self-supervised and unsupervised learning methods for temporal data using invariant theory and harmonic analysis.

Before beginning my Ph.D., I earned my Bachelor’s degree in Electrical and Electronics Engineering from the Middle East Technical University (METU) with a specialization in signal processing. I then pursued a Master’s degree in Electrical Engineering and Computer Science (EECS) at the University of California, Irvine, where I worked on designing real-time systems and algorithms, focusing on signal processing and machine learning for resource-constrained mobile systems, such as wearable devices.

Latest posts

Selected publications

  1. Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning
    Berken Utku Demirel, and Christian Holz
    In The Thirteenth International Conference on Learning Representations, 2025
  2. An Unsupervised Approach for Periodic Source Detection in Time Series
    Berken Utku Demirel, and Christian Holz
    In Forty-first International Conference on Machine Learning, 2024
  3. Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning
    Berken Utku Demirel, and Christian Holz
    In Thirty-seventh Conference on Neural Information Processing Systems, Aug 2023
  4. ICASSP
    ICASSP_polyphase.png
    Cancelling Intermodulation Distortions for Otoacoustic Emission Measurements with Earbuds
    Berken Utku Demirel, Khaldoon Al-Naimi, Fahim Kawsar, and 1 more author
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Aug 2023