Description
Machine learning/Neuro day
-
Prof. Christian SZEGEDY (Google Research)12/05/2022 09:00
Here I will discuss the frontier of research for formal reasoning via deep neural networks. I will highlight the most recent progress in the area, especially automated theorem proving and automated formalization of natural language text. Also, I will discuss the role of language models, contrastive training, retrieval augmented modeling, and reinforcement learning toward the long-term goal of...
Aller à la page de la contribution -
Prof. Josef URBAN (CIIRC)12/05/2022 10:00
The talk will make a (doomed?) attempt to convince the physicists in the audience that machine-based logic and proof combined with machine-based learning is a creeping revolution in science threatening their job security. In principle, I would like to ground it in at least some examples and demos of today's feedback loops between reasoning, conjecturing, and learning systems for math. But...
Aller à la page de la contribution -
Prof. Patrick MASSOT (LMO, Université Paris-Saclay)12/05/2022 11:30
A growing number of mathematicians are having fun explaining mathematics to computers using proof assistant softwares. This process is called formalization. In this talk, I'll describe what formalization looks like, what kind of things it teaches us, and how it could even turn out to be useful (in our usual sense of "useful"). This will not be a talk about the foundations of mathematics, and I...
Aller à la page de la contribution