Optimal Control of Deep Neural Networks by E. Zuazua

On November 9th, our Head Enrique Zuazua will be talking about “Optimal Control of Deep Neural Networks” on the “New Bridges between Mathematics and Data Science” organized by the University of Valladolid on November 8th. – 11th, 2021.

Asbtract. We discuss the training process for Deep Neural Networks (DNN) from an optimal control perspective. In particular we analyze the turnpike phenomena, and how it emerges, as a function of the cost functional to be optimized, and that guarantees that, in the deep layer regime, the DNN experiences the tendency to become steady.

This lecture is inspired on recent joint work with Borjan Geshkovski, Carlos Esteve-Yagüe and Dario Pighin.

WHEN?

Talk by Prof. Enrique Zuazua:

Wed. November 10, 2021 at 17:00H – 19:00H

WHERE?

Online Zoom /On site: Valladolid (Paraninfo)

Registration

To attend this event a registration fee is required. See more The Spanish ‘Mathematical Strategic Network’

|| See more the Complete Program

The event is finished.

No Responses

© 2019-2022 FAU DCN-AvH Chair for Dynamics, Control and Numerics - Alexander von Humboldt Professorship at Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany | Imprint | Contact