A
Andreas Mardt
Researcher at Free University of Berlin
Publications - 12
Citations - 764
Andreas Mardt is an academic researcher from Free University of Berlin. The author has contributed to research in topics: Markov chain & Deep learning. The author has an hindex of 6, co-authored 10 publications receiving 565 citations.
Papers
More filters
Journal ArticleDOI
VAMPnets for deep learning of molecular kinetics.
TL;DR: A deep learning framework that automates construction of Markov state models from MD simulation data is introduced that performs equally or better than state-of-the-art Markov modeling methods and provides easily interpretable few-state kinetic models.
Journal ArticleDOI
VAMPnets: Deep learning of molecular kinetics
TL;DR: In this paper, the authors employ the variational approach for Markov processes (VAMP) to develop a deep learning framework for molecular kinetics using neural networks, dubbed VAMPnets, which encodes the entire mapping from molecular coordinates to Markov states.
Journal ArticleDOI
Author Correction: VAMPnets for deep learning of molecular kinetics.
TL;DR: In the original version of this Article, financial support from the Deutsche Forschungsgemeinschaft Grant SFB958/A04 was not fully acknowledged.
Posted Content
Deep Generative Markov State Models
TL;DR: In this article, a deep generative Markov State Model (DeepGenMSM) is proposed for inference of metastable dynamical systems and prediction of trajectories, which can be operated in a recursive fashion to generate trajectories to predict the system evolution from a defined starting state and propose new configurations.
Posted Content
Deep learning Markov and Koopman models with physical constraints
TL;DR: It is proved that the model is an universal approximator for reversible Markov processes and that it can be optimized with either maximum likelihood or the variational approach ofMarkov processes (VAMP).