Demirel, Berken Utku

6 publications

NeurIPS 2025 Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections Berken Utku Demirel, Christian Holz

ICLR 2025 Shifting the Paradigm: A Diffeomorphism Between Time Series Data Manifolds for Achieving Shift-Invariancy in Deep Learning Berken Utku Demirel, Christian Holz

ICML 2024 An Unsupervised Approach for Periodic Source Detection in Time Series Berken Utku Demirel, Christian Holz

NeurIPS 2024 WildPPG: A Real-World PPG Dataset of Long Continuous Recordings Manuel Meier, Berken Utku Demirel, Christian Holz

UAI 2023 BeliefPPG: Uncertainty-Aware Heart Rate Estimation from PPG Signals via Belief Propagation Valentin Bieri, Paul Streli, Berken Utku Demirel, Christian Holz

NeurIPS 2023 Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning Berken Utku Demirel, Christian Holz