Berken Utku Demirel

berken.demirel.jpg

I am currently a fourth-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 methods for temporal data using harmonic analysis.

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.

Selected publications

  1. Temporal-Scale Sensitivity in Time-Series Tokenization and Scale-Robust Token Estimation by Gated Sum
    Berken Utku Demirel and Christian Holz
    In The Fortieth Conference on Neural Information Processing Systems (NeurIPS), 2026
    PDF (TO APPEAR)
  2. EgoHRV: Continuous Heart Rate Variability Estimation from Egocentric Systems for Autonomic Response and Skill Assessment
    Berken Utku Demirel and Christian Holz
    In European Conference on Computer Vision (ECCV), 2026
    arXiv PDF Code
  3. Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections.
    Berken Utku Demirel and Christian Holz
    In Thirty-ninth Conference on Neural Information Processing Systems (NeurIPS), 2025
    arXiv PDF Code
  4. 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 (ICLR), 2025
    arXiv PDF Code
  5. An Unsupervised Approach for Periodic Source Detection in Time Series
    Berken Utku Demirel and Christian Holz
    In Forty-first International Conference on Machine Learning (ICML), 2024
    arXiv PDF Code
  6. 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 (NeurIPS), 2023
    arXiv PDF Code
  7. Cancelling Intermodulation Distortions for Otoacoustic Emission Measurements with Earbuds
    Berken Utku Demirel, Khaldoon Al-Naimi, Fahim Kawsar, and Alessandro Montanari
    In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (Top 3%), 2023
    PDF

Full publication list →