Machine Learning And Control Theory
Abstract

We discuss the connections between Machine Learning and Control Theory. For instance, Reinforcement Learning uses the formalism of MDP, Markov Decision Processes. On the other hand, Machine learning can be helpful to handle control problems oflarge dimensions . Itturns out that some authors have shown that deep learning can be considered as a control problem, in which time corresponds to the level of layers. We also discuss the connection between identification and learning, the joint learning and decision-making problem, with Bayesian approaches.

Speaker: Professor Alain BENSOUSSAN
Date: 17 June 2020 (Wed)
Time: 11:00am - 12:00pm
PosterClick here

Biography

Professor Alain Bensoussan is Chair Professor of Risk and Decision Analysis at the City University Hong Kong, Lars Magnus Ericsson Chair and the Director of ICDRiA (International Center for Decision and Risk Analysis) at the University of Texas at Dallas. He has been for 4 years World Class University Distinguished Professor at Ajou University. He is Professor Emeritus at the University Paris Dauphine. Professor Bensoussan served as President of National Institute for Research in Computer Science and Control (INRIA) from 1984 to 1996; President of the French Space Agency (CNES) from 1996 to 2003; and Chairman of the European Space Agency CESA) Council from 1999 to 2002. He is a member of the French Academy of Sciences, French Academy of Technology, Academia Europae, and International Academy of Astronautics. His distinctions include AMS Fellow, IEEE Fellow, SIAM Fellow, Von Humboldt award, and the NASA public service medal. Professor Bensoussan is a decorated Officer of Legion d'Honneur, Commandeur Ordre National du Merite from France and Officer Bundes Verdienst Kreuz from Germany. He has received the W.T. and Idalia Reid Prize from SIAM in 2014.