You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Probabilistic Deep Learning finds its application in autonomous vehicles and medical diagnoses. This is an increasingly important area of deep learning that aims to quantify the noise and uncertainty that is often present in real-world datasets.
Exploration of TensorFlow-2 and TensorFlow probability to implement Bayesian Neural Networks, Normalizing flows, real NVPs and Autoencoders. Exploration of Bayesian Modelling and Variational Inference with Pyro.
Detailed implementations, Jupyter tutorials and complete packages to implement and test Probabilistic Bayesian Deep Learning models. The repository contains the software implementations of the techniques discussed in the review paper "Shedding light on uncertainties in machine learning: formal derivation and optimal model selection".