collaborators

7 papers

eess.SY2026

Online learning of neural state-space models

Bendegúz Györök, Tamás Péni, Maarten Schoukens +1

Recent advances in deep-learning-based nonlinear system identification have led to encoder-based estimation of neural state-space (ANN-SS) models that achieve state-of-the-art perf…

eess.SY2026

Efficient stochastic model-predictive control based on the meta-state-space representation

Bendegúz Györök, Roland Tóth, Maarten Schoukens +1

Stochastic model-predictive control (SMPC) has evolved to a powerful framework for the control of stochastic dynamical systems. SMPC utilizes a probabilistic uncertainty descriptio…

eess.SY2026

Data-driven augmentation of first-principles models under constraint-free well-posedness and stability guarantees

Bendegúz Györök, Roel Drenth, Chris Verhoek +3

The integration of first-principles models with learning-based components, i.e., model augmentation, has gained increasing attention, as it offers higher model accuracy and faster…

eess.SY2026

Learning-based augmentation of first-principle models: A linear fractional representation-based approach

Jan H. Hoekstra, Bendegúz M. Györök, Roland Tóth +1

Nonlinear system identificationhas proven to be effective in obtaining accurate models from data for complex real-world systems. In particular, recent encoder-based methods with ar…

eess.SY2026

Encoder initialisation methods in the model augmentation setting

J. H. Hoekstra, B. Györök, R. Töth +1

Nonlinear system identification (NL-SI) has proven to be effective in obtaining accurate models for highly complex systems. Recent encoder-based methods for artificial neural netwo…

eess.SY2026

Orthogonal-by-construction augmentation of physics-based input-output models

Bendegúz M. Györök, Maarten Schoukens, Tamás Péni +1

This paper proposes a novel orthogonal-by-construction parametrization for augmenting physics-based input-output models with a learning component in an additive sense. The parametr…