We're excited to announce posteriors! posteriors is an open-source Python library designed to make it as easy as possible to apply uncertainty quantification to deep learning models with PyTorch. github.com/normal-computi…

Robust decision making needs to handle complex uncertainty. In the context of deep learning, uncertainty quantification is particularly important because neural networks are often overconfident in their predictions or generations.

@NormalComputing @predict_addict

@NormalComputing You mention deep learning but I don’t see that in the readme… an example of the library applied to a large and interesting model would be great… just how large a model can you reasonably handle with this?

@NormalComputing Great name.