Turnpike Control and Deep Learning
The turnpike principle, ubiquitous in applications, asserts that in long time horizons optimal control strategies are nearly of a steady state nature. In this lecture we shall survey on some recent results on this topic and present some its consequences on deep supervised learning, and, in particular, in Residual Neural Networks.
December 10th at 14:00H
(link 5min before session)
See more details at the MOX’s event page
Enrique Zuazua Alexander von Humboldt Professorship | Head of the Chair of Computational Mathematics | Professor of Applied MathematicsEnrique ZuazuaAlexander von Humboldt Professorship | Head of the Chair of Computational Mathematics | Professor of Applied Mathematics
Enrique Zuazua (Eibar, Basque Country – Spain, 1961) holds an Alexander von Humboldt Professorship at the Friedrich–Alexander University (FAU), Erlangen (Germany). He is also the Director of the Chair of Computational Mathematics at Deusto Foundation, Universidad de Deusto (Bilbao, Basque Country-Spain) where he leads the research team funded by the ERC Advanced Grant DyCoN project. He is also a Professor of Applied Mathematics since 2001 at the Department of Mathematics of the Autonomous University of Madrid where he holds a Strategic Chair.
more about Enrique