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