Introduction

The recent use of machine learning in high stakes applications has been pushing many industrial actors to rethink how safety-critical systems (such as planes or cars) can be certified before being manufactured and used. Key questions have emerged, such as: how to properly define safety of systems with learning components? how to formally guarantee safety? which new mathematical guarantees would be needed from the ML research community?

This workshop will bring together machine learning researchers with international authorities and industrial experts from sectors where certification and reliability is a critical issue. It will consist of invited talks, a poster session, and group discussions. The goal is to present key open industrial questions, traditional methods in critical software verification and certification (and AI-related challenges), as well as an introduction to several promising mathematical theories (distribution-free uncertainty quantification, deep learning theory, formal methods, and rigorous numerics).

This workshop is organized by the DEEL project1. We hope this workshop will help shape the future research agenda toward the middle-term objective of certifying critical systems involving AI components.


  1. DEEL is a research program operated by IVADO, IRT Saint Exupéry, CRIAQ, ANITI, IID ↩︎

Talks

People

This workshop is organized by the DEEL project

Invited Speakers

Avatar

Aaditya Ramdas

Assistant Professor in Statistics and Machine Learning

Carnegie Mellon University

Avatar

Antoine Miné

Professor in Computer Science

Sorbonne University

Avatar

Daniel Roy

Associate Professor in statistical science

University of Toronto Scarborough

Avatar

Guillaume Soudain

Critical Software Senior Expert

European Union Aviation Safety Agency (EASA)

Avatar

Martin Vechev

Professor in Computer Science

ETH Zurich

Avatar

Matthieu Cord

Professor in Computer Science

Sorbonne University & Part-time Principal Scientist at valeo.ai

Avatar

Mioara Joldes

Researcher in Computer Science

LAAS - CNRS

Organizers

Avatar

Adrien Gauffriau

Critical Avionics Software Engineer

Airbus & IRT Saint Exupery

Avatar

Baptiste Lefevre

Advanced Technologies Regulation Manager

Thales

Avatar

Fanny Eyboulet

Scientific Project Manager

University of Laval

Avatar

Foutse Khomh

Professor in Computer Science

Polytechnique Montreal

Avatar

Francois Laviolette

Professor in Artificial Intelligence

University of Laval

Avatar

Mélanie Ducoffe

Research Engineer

Airbus & IRT Saint Exupery

Avatar

Sébastien Gerchinovitz

Research Scientist

IRT Saint Exupery & University of Toulouse

Avatar

Yann Pequignot

Scientific Coordinator

University of Laval

Additional Program Committee

Avatar

Edouard Pauwels

Assistant Professor in Mathematics and Computer Science

Institut de Recherche en Informatique de Toulouse & ANITI

Avatar

Franck Mamalet

Research Scientist

IRT Saint Exupery

Avatar

Giuliano Antoniol

Professor of Software Engineering

Polytechnique Montréal

Avatar

Gregory Flandin

DEEL Program Director

IRT Saint-Expuery

Avatar

Jean-Michel Loubes

Professor of Mathematics

Institut de Mathématiques de Toulouse & ANITI

Avatar

Mathieu Serrurier

Assistant Professor in Computer Science

Institut de Recherche en Informatique de Toulouse & ANITI