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

Bayesian Neural Networks with Parallelized Sampling of LogLikelihood

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).