Center for Informatics and Computational Science's repositories
pde-surrogate
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
cnn-surrogate
Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification
ar-pde-cnn
Physics-constrained auto-regressive convolutional neural networks for dynamical PDEs
rans-uncertainty
Uncertainty Quantification of RANS Data-Driven Turbulence Modeling
cnn-inversion
Deep autoregressive neural networks for high-dimensional inverse problems
CAAE-DRDCN-inverse
Deep residual networks for dimensionality reduction and surrogate modeling in high-dimensional inverse problems
structured-gpflow
Gaussian process models with structured inputs based on GPflow
sgplvm-inverse
Experiments using the structured Bayesian Gaussian process latent variable model for inverse problems
predictive-cvs
Predictive collective variable discovery with deep Bayesian models for atomistic systems.
sgp-experiments
Experiments using the structured GP, GP-LVM, and warped GP.