Dipartimento di Informatica

Date: Fri 25 Sep 2020
Time: 10:00 AM
Venue: http://meet.google.com/xqj-mswe-wbv
Speaker: Emanuele Rodolà

Title: Towards geometry-inspired automated reasoning

Abstract: In this talk I will present several recent directions of research in the areas of machine learning and applied AI, developed with my group at Sapienza. Common to these topics are the notions of geometry and structure. I'll start by showing how data-driven methods can serve as efficient and robust drop-in replacements for classical axiomatic constructions, even when learning is not necessary, for typical tasks of geometry and signal processing; in turn, I'll show how geometry itself can serve as a valid proxy for better machine learning pipelines. I'll then explore some preliminary steps toward the development of an AI capable of reasoning about abstract concepts. Once again, structure will be the leitmotif of the proposed ideas, and will be used to establish a tentative (and reckless) relation between language, geometry, and intelligence.