Physics-constrained auto-regressive convolutional neural networks for dynamical PDEs

Gaussian processes with PyTorch

Deep residual networks for dimensionality reduction and surrogate modeling in high-dimensional inverse problems

Uncertainty Quantification of RANS Data-Driven Turbulence Modeling

Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification

Predictive collective variable discovery with deep Bayesian models for atomistic systems.

Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data

Deep autoregressive neural networks for high-dimensional inverse problems

Deep convolutional encoder-decoder networks for uncertainty quantification of dynamic multi-phase flow in heterogeneous random media

Gaussian process models with structured inputs based on GPflow