Philipp Hennig Profile picture
Professor for the Methods of Machine Learning at the University of Tübingen.
Jun 28, 2022 6 tweets 3 min read
It’s out! Oh boy!

Probabilistic Numerics: big ideas for the internals of learning machines — and now also a BOOK, w/ @maosbot and @HansKersting!

What is #ProbabilisticNumerics, and why does it matter for ML? Thread below, with a link to a free pdf of the book at the end :) A picture of the book “Prob... We hear a lot about *models* in ML. But what actually happens within the “machine” during learning is a *numerical* task: Optimization (for loss minimization), Integration (for Bayesian inference), Simulation (for control, RL, physics,..). Linear Algebra for, well, everything.