Deep learning of molecular kinetics

Andreas Mardt
Freie Universität Berlin
Mathematics and Informatics

We employ the recently developed variational approach for Markov processes (VAMP) to develop a deep learning framework for molecular kinetics using neural networks, dubbed VAMPnets. A VAMPnet encodes the entire mapping from molecular coordinates to Markov states and learns optimal feature transformations, non-linear dimension reduction, cluster discretization and MSM estimation within a single end-to-end learning framework.

Back to Machine Learning for Physics and the Physics of Learning