Description du projet
Justifier les décisions prises par l’IA
L’intelligence artificielle (IA) de type «boîte noire», combinée à l’apprentissage automatique, est utilisée de manière généralisée dans la prise de décision automatisée. Elle permet de gérer les données et de traiter rapidement les décisions, décisions automatisées qui, par ailleurs, peuvent être fondées sur un parti pris lié aux données collectées ou être injustes. Ne pouvant être ni expliquées ni transparentes, ces décisions privent les clients de leur droit à obtenir des explications. Le projet XAI, financé par l’UE, vise à produire des explications pertinentes pour les systèmes d’intelligence artificielle et d’apprentissage automatique. Les recherches s’intéressent à la manière de concevoir la transparence dans les modèles d’apprentissage automatique, de produire des explications contrôlées relatives à la boîte noire, de révéler les données et les algorithmes utilisés ainsi que l’injustice et les relations de causalité des processus. Le projet formulera également des normes éthiques et juridiques relatives à l’IA.
Objectif
A wealthy friend of mine asks for a vacation credit card to his bank, to discover that the credit he is offered is very low. The bank teller cannot explain why. My stubborn friend continues his quest for explanation up to the bank executives, to discover that an algorithm lowered his credit score. Why? After a long investigation, it turns out that the reason is: bad credit by the former owner of my friend’s house.
Black box AI systems for automated decision making, often based on ML over (big) data, map a user’s features into a class or a score without explaining why. This is problematic for lack of transparency, but also for possible biases inherited by the algorithms from human prejudices and collection artefacts hidden in the training data, which may lead to unfair or wrong decisions.
I strive for solutions of the urgent challenge of how to construct meaningful explanations of opaque AI/ML systems, introducing the local-to-global framework for black box explanation, articulated along 3 lines: a) the language for explanations in terms of expressive logic rules, with statistical and causal interpretation; b) the inference of local explanations for revealing the decision rationale for a specific case; c), the bottom-up generalization of many local explanations into simple global ones. An intertwined line of research will investigate both causal explanations, i.e. models that capture the causal relationships among the features and the decision, and mechanistic/physical models of complex system physics, that capture the data generation mechanism behind specific deep learning models.
I will also develop: an infrastructure for benchmarking, for the users' assessment of the explanations and the crowdsensing of observational decision data; an ethical-legal framework, for compliance and impact of our results on legal standards and on the “right of explanation” provisions of the GDPR; case studies in explanation-by-design, with a priority in health and fraud detection.
Champ scientifique
Mots‑clés
Programme(s)
Thème(s)
Régime de financement
ERC-ADG - Advanced GrantInstitution d’accueil
56126 Pisa
Italie