Numerics of ML 13 -- Uncertainty in Deep Learning -- Agustinus Kristiadi

Описание: The thirteenth lecture of the Master class on Numerics of Machine Learning at the University of Tübingen in the Winter Term of 2022/23.

This class discusses both practical and theoretically interesting aspects of the algorithms that drive machine learning. It endorses the view of Probabilistic Numerics, the idea that computation itself is an inference process, to describe the numerical algorithms inside the learning machine, as learning machines.

The slides for the course are available at https://github.com/philipphennig/Nume.... All slides come with embedded, time-stamped links to these youtube videos (click on the icon on the bottom right of each slide).

The class is being taught in the winter term 2022/23. Videos are uploaded here in semantic groups over the course of January and February 2023.