Séminaire - A Panorama of Neural Networks and Deep Learning - Patrick Gallinari

IMPMC - Sorbonne Université - 4 place Jussieu, 75005 Paris, tour 23, 4e étage, couloir 22-23, salle 401

Mardi 25 juin 2019 à 14 h

Patrick Gallinari (SU-LIP6, Criteo AI Lab)

Abstract

The recent rise of modern Artificial Intelligence has been supported by large scale operational deployments of machine learning algorithms. The dominant technology today in this field is Deep Learning, the modern name of an older technology – Artificial Neural Networks. After a brief historical perspective of the domain, I will introduce the main challenges and the concepts behind the techniques of Deep Learning. This will be further illustrated by some applications. I will also introduce some recent ideas aiming at combining Deep Learning and Physics for the modeling of spatio-temporal processes.

Patrick Gallinari is a professor at Sorbonne University and researcher at Criteo AI Lab - Paris. His research focuses on statistical learning and deep learning with applications in different fields such as semantic data processing or complex data analysis.  Together with colleagues from Sorbonne University, he started to explore in 2017 the development of physico-statistical systems combining the model based approaches of physics and the data processing approaches of statistical learning. He has been a pioneer in the development of Neural Networks in the 90ies.  He leads a team whose central theme is Statistical Learning and Deep Learning (https://mlia.lip6.fr). He was director of the Paris 6 computer lab (LIP6) for 9 years (2005 to 2013).