Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.

The repository is the implementation of a research paper concluding the performance analysis of machine learning algorithm on complex non-Newtonian fluids.

Bayesian Neural Networks with Parallelized Sampling of LogLikelihood

Variational Auto-Encoder with uncertainty quantification using BNN and variational inference.

Software for flexible Bayesian modelling and Markov chain sampling.

An implementation of WideResNets with Fixup initialization in Jax/Flax. This can be useful for use cases where Batch Normalization should be avoided (for example when using the Laplace approximation to the Bayesian posterior).