New version of the PC tutorial, with code snippets to learn PCs and perform inference on them in python and Julia
Can simple deterministic autoencoders learn meaningful and smooth latent spaces? If yes, how can we turn them into generative models?. Invited talk at UCL AI Centre.
How tractable probabilistic inference can enable and support decision making in the real-world. With my very personal of iterated inference and exploratory predictive analysis. Invited talk at the PL and PIO groups at the MPI.
The most comprehensive version of the tutorial on probabilistic circuits. It conteins an expanded section on learning by Robert and connections to logical circuits by YooJung.
Introductory talk for the first meeting on tractable probabilistic inference we organized as a social event at NeurIPS 2019.
Revisited version of the UAI 2019 tutorial, emphasizing the connections and differences between probabilistic circuits and the current landscape of deep generative models.
Navigating through the alphabet soup of probabilistic models and charting the spectrum of tractable inference.
Introducing probabilistic circuits as a unifying framework for tractable probabilistic inference.
ECCAI invited tutorial with introductory material on Sum-Product Networks for the PGM community.