Zobrazeno 1 - 10 of 45 pro vyhledávání: '"Stephan Thaler"'
1
Akademický článek
Active learning graph neural networks for partial charge prediction of metal-organic frameworks via dropout Monte Carlo
Autor: Stephan Thaler, Felix Mayr, Siby Thomas, Alessio Gagliardi, Julija Zavadlav
Publikováno v: npj Computational Materials, Vol 10, Iss 1, Pp 1-10 (2024)
Abstract Metal-organic frameworks (MOF) are an attractive class of porous materials due to their immense design space, allowing for application-tailored properties. Properties of interest, such as gas sorption, can be predicted in silico with molecul
Externí odkaz: https://doaj.org/article/d2e97b0c31f24722b4f5af7dfd391676
Zobrazit plný text záznamu
2
Akademický článek
JaxSGMC: Modular stochastic gradient MCMC in JAX
Autor: Stephan Thaler, Paul Fuchs, Ana Cukarska, Julija Zavadlav
Publikováno v: SoftwareX, Vol 26, Iss , Pp 101722- (2024)
We present JaxSGMC, an application-agnostic library for stochastic gradient Markov chain Monte Carlo (SG-MCMC) in JAX. SG-MCMC schemes are uncertainty quantification (UQ) methods that scale to large datasets and high-dimensional models, enabling trus
Externí odkaz: https://doaj.org/article/57ca245c77024290b48775c5a998e863
Zobrazit plný text záznamu
3
Akademický článek
Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
Autor: Stephan Thaler, Julija Zavadlav
Publikováno v: Nature Communications, Vol 12, Iss 1, Pp 1-10 (2021)
In machine learning approaches relevant for chemical physics and material science, neural network potentials can be trained on the experimental data. The authors propose a training method applying trajectory reweighting instead of direct backpropagat
Externí odkaz: https://doaj.org/article/6c34aa6706384e3b9d43a8893868e6f3
Zobrazit plný text záznamu
4
Scalable Bayesian Uncertainty Quantification for Neural Network Potentials: Promise and Pitfalls
Autor: Stephan Thaler, Gregor Doehner, Julija Zavadlav
Neural network (NN) potentials promise highly accurate molecular dynamics (MD) simulations within the computational complexity of classical MD force fields. However, when applied outside their training domain, NN potential predictions can be inaccura
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::88695aadcf2a753b7fd01e75afb6362a
http://arxiv.org/abs/2212.07959
Zobrazit plný text záznamu
5
Deep Coarse-grained Potentials via Relative Entropy Minimization
Autor: Stephan Thaler, Maximilian Stupp, Julija Zavadlav
Neural network (NN) potentials are a natural choice for coarse-grained (CG) models. Their many-body capacity allows highly accurate approximations of the potential of mean force, promising CG simulations at unprecedented accuracy. CG NN potentials tr
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1ab129f32cf096480efb96cf8effc784
http://arxiv.org/abs/2208.10330
Zobrazit plný text záznamu
9
Sparse identification of truncation errors
Autor: Nikolaus A. Adams, Stephan Thaler, Ludger Paehler
Publikováno v: Journal of Computational Physics. 397:108851
This work presents a data-driven approach to the identification of spatial and temporal truncation errors for linear and nonlinear discretization schemes of Partial Differential Equations (PDEs). Motivated by the central role of truncation errors, fo
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e6a8da184d4dab3e79a8296926eb8618
https://doi.org/10.1016/j.jcp.2019.07.049
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje