European Commission logo
français français
CORDIS - Résultats de la recherche de l’UE
CORDIS

Argumentation-based Deep Interactive EXplanations(ADIX)

Description du projet

Repenser de manière radicale l’IA explicable

L’intelligence artificielle (IA) offre de nouvelles possibilités et un large éventail d’opportunités dans de nombreux secteurs et domaines, notamment ceux des soins de santé et de la pratique du droit. Le projet ADIX, financé par l’UE, rendra l’IA et ses algorithmes plus explicables et plus transparents aux yeux de personnes issues d’horizons différents. Son objectif cardinal est de favoriser l’adoption de l’IA par les scientifiques et les non-scientifiques et de permettre à ceux-ci de tirer parti de l’apprentissage automatique. ADIX permettra de repenser radicalement le concept d’IA explicable pour une société soutenue par l’IA. En tant que tel, le projet définira un nouveau paradigme scientifique des explications profondes et interactives fondées sur l’argumentation computationnelle, capable d’être déployé parallèlement à un éventail de méthodes d’IA centrées sur les données pour fournir des justifications à leur appui.

Objectif

Today’s AI landscape is permeated by plentiful data and dominated by powerful methods with the potential to impact a wide range of human sectors, including healthcare and the practice of law. Yet, this potential is hindered by the opacity of most data-centric AI methods and it is widely acknowledged that AI cannot fully benefit society without addressing its widespread inability to explain its outputs, causing human mistrust and doubts regarding its regulatory and ethical compliance. Extensive research efforts are currently being devoted towards explainable AI, but they are mostly focused on engineering shallow, static explanations providing little transparency on how the explained outputs are obtained and limited opportunities for human insight. ADIX aims to define a novel scientific paradigm of deep, interactive explanations that can be deployed alongside a variety of data-centric AI methods to explain their outputs by providing justifications in their support. These can be progressively questioned by humans and the outputs of the AI methods refined as a result of human feedback, within explanatory exchanges between humans and machines. This ambitious paradigm will be realised using computational argumentation as the underpinning, unifying theoretical foundation: I will define argumentative abstractions of the inner workings of a variety of data-centric AI methods from which various explanation types, providing argumentative grounds for outputs, can be drawn, generate explanatory exchanges between humans and machines from interaction patterns instantiated on the argumentative abstractions and explanation types, and develop argumentative wrappers from human feedback. The novel paradigm will be theoretically defined and informed and tested by experiments and empirical evaluation, and it will lead to a radical re-thinking of explainable AI that can work in synergy with humans within a human-centred but AI-supported society.

Régime de financement

ERC-ADG - Advanced Grant

Institution d’accueil

IMPERIAL COLLEGE OF SCIENCE TECHNOLOGY AND MEDICINE
Contribution nette de l'UE
€ 2 500 000,00
Adresse
SOUTH KENSINGTON CAMPUS EXHIBITION ROAD
SW7 2AZ LONDON
Royaume-Uni

Voir sur la carte

Région
London Inner London — West Westminster
Type d’activité
Higher or Secondary Education Establishments
Liens
Coût total
€ 2 500 001,25

Bénéficiaires (1)