Skip to main content
Home

Main Navigation - CSMD

  • Home
  • About
  • Research
  • Software
  • Groups
  • Jobs

Data Analytics and Machine Learning

Highlights

Periodic time series
Robust learning with implicit networks
Image inpainting
Feature-driven exemplar-based nonlocal image inpainting
Solution in random domain
Numerical methods for PDEs in random domains
Stiff chemical system
Numerical integration of stiff stochastic chemical systems
Conceptual comparison of (a) the standard multi-loop Monte Carlo method for propagating multiple probability models, and (b) the proposed multimodel Monte Carlo method with importance sampling reweighting
Monte Carlo Methods for UQ: A Survey
 A diagram of the workflow of our method.
A data-driven approach to study the thermodynamics of high entropy alloys
Probabilistic dependent input models
Uncertainty quantification with copula dependence modeling
CDF of imprecise first-order Sobol’ indices as a function of data set size from 100, 250, 500, 1000, 5000 to 10000.
IGSA: Imprecise global sensitivity analysis
Composite materials applications
Probabilistic modeling of composite materials with sparse data
DNN_RM
Non-intrusive inference reduced order model for fluids using deep multistep neural network
exit-2d
A Feynman-Kac based numerical method for the exit time probability of a class of transport problems
RE_sg
A sparse-grid probabilistic scheme for approximation of the runaway probability of electrons in fusion tokamak simulation
RE_MC
A backward Monte-Carlo method for time-dependent runaway electron simulations
quantum control
A stochastic approximate gradient ascent method for Bayesian experimental design with implicit models
Ackley function
AdaDGS: An adaptive black-box optimization method with a nonlocal directional Gaussian smoothing gradient

Pagination

  • Current page 1
  • Page 2
  • Next page ››
  • Last page Last »

Stay Connected

Please send questions or comments to packdl@ornl.gov. 

  • Privacy
  • Accessibility/508
  • Nondiscrimination/1557
UT-Battelle
Department of Energy - Office of Science