Deep learning for variational multiscale molecular modeling
نویسندگان
چکیده
منابع مشابه
Stochastic Variational Deep Kernel Learning
Deep kernel learning combines the non-parametric flexibility of kernel methods with the inductive biases of deep learning architectures. We propose a novel deep kernel learning model and stochastic variational inference procedure which generalizes deep kernel learning approaches to enable classification, multi-task learning, additive covariance structures, and stochastic gradient training. Spec...
متن کاملAIAA 2002-3280 Variational Multiscale Modeling for Turbulence Control
We explore the capabilities of the variational multiscale (VMS) method in the context of turbulence control by applying VMS to the simulation of a simple opposition control strategy for turbulent channel flow with the results compared to prior direct numerical simulations and large-eddy simulations (LES). In all cases, the VMS method is found to be more efficient and more accurate than traditio...
متن کاملVariational Networks: Connecting Variational Methods and Deep Learning
In this paper, we introduce variational networks (VNs) for image reconstruction. VNs are fully learned models based on the framework of incremental proximal gradient methods. They provide a natural transition between classical variational methods and state-of-the-art residual neural networks. Due to their incremental nature, VNs are very efficient, but only approximately minimize the underlying...
متن کاملOn Modern Deep Learning and Variational Inference
Bayesian modelling and variational inference are rooted in Bayesian statistics, and easily benefit from the vast literature in the field. In contrast, deep learning lacks a solid mathematical grounding. Instead, empirical developments in deep learning are often justified by metaphors, evading the unexplained principles at play. It is perhaps astonishing then that most modern deep learning model...
متن کاملMultiscale modeling of liquids with molecular specificity.
The separation between molecular and mesoscopic length and time scales poses a severe limit to molecular simulations of mesoscale phenomena. We describe a hybrid multiscale computational technique which addresses this problem by keeping the full molecular nature of the system where it is of interest and coarse graining it elsewhere. This is made possible by coupling molecular dynamics with a me...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: The Journal of Chemical Physics
سال: 2020
ISSN: 0021-9606,1089-7690
DOI: 10.1063/5.0026836