In this work, we propose a data-driven reformulation of the identification of CVs under the paradigm of probabilistic (Bayesian) inference. The methodology ...
Sep 18, 2018 · In this work, we formulate the discovery of CVs as a Bayesian inference problem and consider the CVs as hidden generators of the full-atomistic trajectory.
Results of the following publication are based on this implementation: Predictive Collective Variable Discovery with Deep Bayesian Models. Dependencies. Python ...
The discovery of CVs is formulated as a Bayesian inference problem and the CVs are considered as hidden generators of the full-atomistic trajectory to ...
The methodology is based on emerging methodological advances in machine learning and variational inference. The discovered CVs are related to physicochemical ...
Predictive Collective Variable Discovery with Deep Bayesian Models in Atomistic Systems. M. Schöberl1,2,3, N. Zabaras1, P.-S. Koutsourelakis2 meeting venue.
Predictive Collective Variable Discovery with Deep Bayesian Models. Author. Koutsourelakis Phaedon-Stelios · Schöberl Markus · Zabaras Nicholas. Publication ...
Predictive collective variable discovery with deep Bayesian models for atomistic systems. ... Deep residual networks for dimensionality reduction and surrogate ...
In this work, we assess the predictive capabilities of a molecular generative model developed based on variational inference and graph theory in the small data ...
... Predictive collective variable discovery with deep Bayesian models", Journal of Chemical Physics, Vol. ... Girolami, "Special Issue: Big data and predictive ...