The second workshop will mainly focus on getting some insights on a more computer scientists' persepective on deep learning.

  • Date: 06 JULY 2022  from 10:00 to 13:00

  • Event location: Seminario II, Dipartimento di Matematica, Università di Bologna, P.zza di Porta S. Donato 5, 40126 Bologna, Italy - In presence and online event

  • Type: Online-Onsite Workshops

As part of the Una Europa funded grant TOC4Deep (Tensor-based Optimal Control Approaches for Deep Learning) a series of half-day workshops will be held over the next 6 months to encourage scientific networking and discussions between the project universities of Edinburgh, Bologna and KU Leuven. The second of these workshops will take place on Wednesday 06th July, with a main focus on computer scientists' perspective on machine and deep learning. The workshop will be hybrid, with in person attendance in Seminario II, Dipartimento di Matematica, University of Bologna, or via Zoom (link to follow). 

The timetable and speaker information is below:

Time (CEST) please mind the time zone

10.15-10.30 -  Introduction/TOC4Deep presentation and preliminary results

10.30-11.15 - Brecht Evens - KU Leuven

Neural Network Training as an Optimal Control Problem: An Augmented Lagrangian Approach

11.15-11.30 - Break

11.30-12.15 - Andrea Asperti - University of Bologna

Comparing the Latent Space of Generative Models

12.15-13 - Antonio Vergari - University of Edinburgh

A Unifying Reasoning Framework for Trustworthy ML