Worldwide. On December 10th. our Head Enrique Zuazua talked about “Turnpike control and deep learning”, a seminar organized by the MOX Politecnico di Milano.
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.
This lecture is based on joint work with our team member Carlos Esteve, Borjan Geshkovski and Dario Pighin.
JOIN THIS SESSION VIA ZOOM
(link 5min before session)
See more details at the MOX’s event page