1. Accueil
  2. EN
  3. Research
  4. Research projects
  5. Belgium
  6. EOS projects

EOS research project "Verifying Learning Artificial Intelligence Systems"

“With great power comes great responsibility” is a cliché that perfectly applies to artificial intelligence (AI). As technology is progressing faster, humans are still lacking the tools to systematically obtain strong guarantees - about their safety, privacy, etc. - from the intelligent software that serves them.
A solution could be computer aided verification: this discipline consists in devising automated methods and tools to improve the dependability of computer-based systems. Although remarkable progress during the past decades, automated verification is not yet applicable to systems using AI or machine learning technology. This project aims to remove these limitations by investigating the logical and probabilistic underpinnings of verification, machine learning and AI. The expected results are new theories, formalisms and algorithms that will constitute the foundations for a new generation of AI-ready verification methods and tools.
The project gathers researchers from ULB (Emmanuel Filiot, Gilles Geeraerts & Jean-François Raskin - Verification and formal methods, Faculty of Sciences), together with researchers from Université de Namur and KULeuven (coordinator).
Dates
Created on August 13, 2018