Abstract: Neural networks excel at finding patterns in large amounts of data, yet they struggle to learn the basic laws of physics. Applying the methods of machine learning to build accurate models of the world thus requires a strong inductive bias, e.g. a notion of symmetry, invariances or… [read more]

Abstract: Machine Learning (ML) is widely utilized in various fields to solve problems and assist research. In the field of medical image synthesis, Deep Learning (DL) shows great potential. Recently, different kinds of frameworks of Generative Adversarial Network (GAN) have been developed.… [read more]

Abstract: Gaussian processes are a well-studied stochastic machine learning method that has proven to be useful in many areas of application. They are flexible due to their non- parametric approach and are able to quantify the uncertainty of their predictions. This work describes the basic… [read more]

Our paper on "Physics-aware, probabilistic model order reduction with guaranteed stability" has been accepted to #ICLR2021.  This year's acceptance rate was 29%. Congratulations to Sebastian Kaltenbach for putting in all the hard work! More details can be found… [read more]

More details here Github repository here [read more]

Abstract:  In this thesis, we try to find a probabilistic Koopman-based representation for dynamical systems. Therefore we apply the framework of [Pan et al 2019], where the author successfully found such representation as a residual improvement of the powerful Dynamic Mode Decomposition technique.… [read more]

Abstract: Accurate modeling of physical systems is of great importance to engineers. In this thesis, we construct novel machine learning models based on the Neural ODE approach in Chen et al. (2018) and compare them to existing architectures. The evaluation is performed on multiple physical systems,… [read more]

[read more]

More details here Github repository here [read more]

Abstract: Inverse problems are ubiquitous in the engineering domain and often rely on computationally expensive forward models. For applications with societal or economical impact it is of major importance to quantify the uncertainties associated with the simulation results. A Bayesian formulation… [read more]