72 citations · 285 across the 18 of their papers we have counts for
19 papers
Informed Equation Learning
Matthias Werner, Andrej Junginger, Philipp Hennig +1
Distilling data into compact and interpretable analytic equations is one of the goals of science. Instead, contemporary supervised machine learning methods mostly produce unstructu…
Invariant Manifolds and Rate Constants in Driven Chemical Reactions
Matthias Feldmaier, Philippe Schraft, Robin Bardakcioglu +7
Reaction rates of chemical reactions under nonequilibrium conditions can be determined through the construction of the normally hyperbolic invariant manifold (NHIM) [and moving div…
Unpaired High-Resolution and Scalable Style Transfer Using Generative Adversarial Networks
Andrej Junginger, Markus Hanselmann, Thilo Strauss +3
Neural networks have proven their capabilities by outperforming many other approaches on regression or classification tasks on various kinds of data. Other astonishing results have…
Binary contraction method for the construction of time-dependent dividing surfaces in driven chemical reactions
Robin Hobil Bardakcioglu, Andrej Junginger, Matthias Feldmaier +2
Transition state theory formally provides a simplifying approach for determining chemical reaction rates and pathways. Given an underlying potential energy surface for a reactive s…
Neural network approach to time-dependent dividing surfaces in classical reaction dynamics
Philippe Schraft, Andrej Junginger, Matthias Feldmaier +4
In a dynamical system, the transition between reactants and products is typically mediated by an energy barrier whose properties determine the corresponding pathways and rates. The…
Ensemble Methods as a Defense to Adversarial Perturbations Against Deep Neural Networks
Thilo Strauss, Markus Hanselmann, Andrej Junginger +1
Deep learning has become the state of the art approach in many machine learning problems such as classification. It has recently been shown that deep learning is highly vulnerable…