Méthodes formelles pour l'intelligence artificielle

Members

Permanent members:

  • Dietmar Berwanger
  • Benedikt Bollig
  • Patricia Bouyer
  • Stéphane Demri
  • Alain Finkel
  • Matthias Függer
  • Paul Gastin
  • Stefan Haar
  • Serge Haddad
  • Mihaela Sighireanu
  • Lina Ye

PhD students:

  • Ashwin Bhaskar (DigiCosme grant, starting in March 2021)
  • Igor Khmelnitsky

Associated member:

  • Philippe Dague (Emeritus Professor)

Keywords

  • Verification of machine learning and artificial intelligence
    • safety and robustness of deep neural networks
    • explainable artificial intelligence
    • scalability of formal verification in machine learning
  • Synthesis and control
    • policy learning in games and probabilistic models
    • reinforcement learning
    • control of cyber-physical systems using deep learning
  • Model learning
    • learning extended automata (weighted, data, transducers, ...)
    • learning network models
    • black-box verification
    • model-based testing
  • Reasoning about knowledge
    • logic (description logic, multi-agent logic, epistemic logic, strategy logic, ...)
    • learning logical concepts
    • probabilistic reasoning (Bayesian networks, hidden Markov models, ...)
    • causality

Projects

  • STIC AmSud – DyLo-MPC: Dynamic Logics: Model Theory, Proof Theory and Computational Complexity
  • IRP – SINFIN: Méthodes formelles pour la modélisation, la spécification, la vérification et le développement de logiciels
  • Égide/Procope – LeaRNNify: New Challenges for Recurrent Neural Networks and Grammatical Inference

Publications

  • F. Belardinelli and S. Demri. Reasoning with a Bounded Number of Resources in ATL+. In Proceedings of the 24th European Conference on Artificial Intelligence (ECAI'20), Santiago de Compostela, Spain, September 2020. IOS Press. To appear.
  • N. Alechina, S. Demri, and B. Logan. Parameterised Resource-Bounded ATL. In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI'20), pages 7040--7046. AAAI Press, February 2020.
  • B. Bednarczyk, S. Demri, and A. Mansutti. A Framework for Reasoning about Dynamic Axioms in Description Logics In Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI'20). IJCAI organization, July 2020.
  • P. Gardy, P. Bouyer, and N. Markey. Dependences in Strategy Logic. Theory of Computing Systems, 64(3), 2020.
  • I. Khmelnitsky, D. Neider, R. Roy, B. Barbot, B. Bollig, A. Finkel, S. Haddad, M. Leucker, L. Ye: Property-Directed Verification of Recurrent Neural Networks. CoRR abs/2009.10610 (2020).
  • F. Belardinelli and S. Demri. Resource-bounded ATL: the Quest for Tractable Fragments. In Proceedings of the 18th International Joint Conference on Autonomous Agents and Multi-Agent Systems (AAMAS'19), pages 206--214, Montreal, Canada, June 2019. ACM Press.
  • P. Bouyer, O. Kupferman, N. Markey, B. Maubert, A. Murano, and G. Perelli. Reasoning about Quality and Fuzziness of Strategic Behaviours. In Proceedings of the 28th International Joint Conference on Artificial Intelligence (IJCAI'19), pages 1588--1594. IJCAI organization, July 2019.
  • S. Demri, R. Fervari, and A. Mansutti. Axiomatising logics with separating conjunctions and modalities. In Proceedings of the 16th European Conference on Logics in Artificial Intelligence (JELIA'19), volume 11468 of Lecture Notes in Artificial Intelligence, pages 692--708, Rende, Italy, June 2019. Springer.
  • N. Alechina, N. Bulling, S. Demri, and B. Logan. On the Complexity of Resource-Bounded Logics. Theoretical Computer Science, 750:69--100, 2018.
  • P. Bouyer, P. Gardy, and N. Markey. On the semantics of Strategy Logic. Information Processing Letters, 116(2):75--79, February 2016.
  • P. Bouyer, P. Gardy, and N. Markey. Weighted strategy logic with boolean goals over one-counter games. In Proceedings of the 35th Conference on Foundations of Software Technology and Theoretical Computer Science (FSTTCS'15), volume 45 of Leibniz International Proceedings in Informatics, pages 69--83, Bangalore, India, December 2015. Leibniz-Zentrum für Informatik.
  • B. Bollig, P. Habermehl, C. Kern, and M. Leucker. Angluin-Style Learning of NFA. In Proceedings of the 21st International Joint Conference on Artificial Intelligence (IJCAI'09), pages 1004-1009, 2009. AAAI Press.