SciML / NeuralPDE.jl

Physics-Informed Neural Networks (PINN) Solvers of (Partial) Differential Equations for Scientific Machine Learning (SciML) accelerated simulation
https://docs.sciml.ai/NeuralPDE/stable/
Other
961 stars 195 forks source link

Bayesian Neural PDEs #205

Open ChrisRackauckas opened 3 years ago

ChrisRackauckas commented 3 years ago

See https://arxiv.org/pdf/2006.04228.pdf as a guiding document. We can essentially have the NNBayesianPDE which is the same as the other but spits out a Bayesian estimation problem a la https://turing.ml/dev/tutorials/3-bayesnn/ with ADVI and use that to train with uncertainties. This would be a great GSoC project.

ChrisRackauckas commented 3 years ago

Another relevant paper: https://arxiv.org/abs/2003.06097