ELLIS Summer School on Large-Scale AI for Research and Industry

Modena, 18-22 September 2023

Presentation

The 2023 ELLIS Summer School on Large-Scale AI is an annual event for ELLIS PhD students, post-docs and fellows to meet in person and share knowledge about Machine Learning, Intelligent Systems and all topics covered by the ELLIS Programs. The theme of the lectures and keynotes of this edition will be “Large-Scale AI for Research and Industry”. The school will focus on advanced scientific research and on the exploitation of European GPU-based HPC facilities. As our research has strong implications and applications in industry, we will also discuss with representatives of industrial research labs.

Highlights

Students of the School will have the opportunity to:

  • attend high-profile lectures and tutorials from top-level scientists
  • attend lab lectures from both academia and industry
  • discuss their work through poster and tooling sessions
  • develop projects on the parallel GPU facilities of the Leonardo Supercomputer hosted by CINECA
  • have fun! 😃

The school takes place in Modena and is organised by the Modena ELLIS Unit, comprising researchers from the University of Modena and Reggio Emilia (UNIMORE), the University of Florence, and CINECA - the Italian Supercomputing Centre.

Keynote Speakers

Monday, 18th

Bernt Schiele  

Max Planck Institute for Informatics

Interpretability for Deep Learning in Computer Vision

Alberto Del Bimbo  

University of Florence

Science Writing - from lived life experiences

Tuesday, 19th

Federico Tombari  

Google Zurich

3D scene understanding for real applications

Laura Leal-Taixé  

NVIDIA and TU Munich

From hand-crafted to end-to-end learning and back: a journey for MOT

Cristian Canton Ferrer  

Head of Responsible AI, Meta

Responsible AI in the age of GenAI: the case of Llama2

During the Social Event at Florim Gallery

Wedsneday, 20th

Nicu Sebe  

University of Trento

Cross-modal Video Generation

Cees Snoek  

Qualcomm QUVA Lab and University of Amsterdam

Learning to Generalize in Video Space and Time

Björn Schuller  

Imperial College London

Think Big: Entering Large Scale Affective Computing

Thursday, 21st

Pietro Perona  

California Institute of Technology, Amazon

Responsible AI: Measuring accuracy and bias in Computer Vision Systems

Mario Fritz  

CISPA Helmholtz Center for Information Security

Trustworthy AI - A Cybersecurity Perspective

Victor Sanh  

Hugging Face

Training an open-access 80 billion parameters vision and language model, lessons learned

Friday, 22nd

Marc'Aurelio Ranzato  

DeepMind

Modular Large-Scale Continual Learning

Tal Hassner  

Meta AI

AI Robustness: What, Why, and How

Tutorial Speakers

Giuseppe Fiameni  

NVIDIA AI Technology Center

Larger-scale model training on multi-GPU systems

Fabian Manhardt  

Google Zurich

Tutorial on 3D Scene Understanding

Sergio Orlandini

CINECA

Larger-scale model training on multi-GPU systems

Social Event and Gala Dinner

A social event with a Gala Dinner will take place on Tuesday at the Florim Gallery in Fiorano Modenese, after a visit to the Ferrari Museum in Maranello. See more. Other social gatherings will be organised in Modena and its surrounding, as well as interactive moments for networking.

Large-Scale student projects

The School will represent a unique opportunity for students to develop and train large-scale Deep Learning projects. In particular, students will be given access to the Booster partition of the Leonardo Supercomputer which contains 3456 computing nodes each equipped with four NVIDIA Ampere GPUs with 64GB, with a 89,4 TFLOPs peak per node. For the School, CINECA has reserved 500 Ampere GPUs for three days. See more.

Organization

The School is organized by the Modena ELLIS Unit, the AImageLab research laboratory and by the Interdipartimental Center on Artificial Intelligence Research and Innovation (AIRI), in cooperation with CINECA and NVIDIA. The School is endorsed by the Dipartimento di Ingegneria “Enzo Ferrari”, the CINI Lab. on Artificial Intelligence and Intelligent Systems, the ELSA, ELISE and FAIR projects. Administrative support and secretariat is provided by Fondazione Marco Biagi.

Sponsors

The School is financially supported by Florim Ceramiche, E4 Computer Engineering, Tetra Pak Packaging Solutions, Nexion and ATON Green Storage.