Belle Lab

The Lab carries out research in artificial intelligence, by blending ideas from machine learning, knowledge representation, automated planning and multi-agent systems.

We are motivated by the need to augment learning and perception with high-level structured, commonsensical knowledge, to enable systems to learn faster and more accurate models of the world. We are interested in developing computational frameworks that are able to explain their decisions, modular, re-usable, and robust to variations in problem description. A non-exhaustive list of topics include:

  • probabilistic and statistical knowledge bases
  • exact and approximate probabilistic inference
  • statistical relational learning
  • unifying deep learning and probabilistic learning methods
  • probabilistic programming
  • numerical optimization
  • automated planning and high-level programming
  • cognitive robotics
  • automated reasoning
  • modal logics (knowledge, action, belief)
  • multi-agent systems and epistemic planning

Principal Investigator: Vaishak Belle

Postdoctoral fellows and PhD students:

  • Amélie Levray (Postdoctoral fellow), interested in tractable learning
  • Giannis Papantonis, interested in probabilistic machine learning
  • Ionela-Georgiana Mocanu, interested in probabilistic programming
  • Gary Smith (principal supervisor: Ron Petrick), interested in program verification
  • Anton Fuxjaeger, interested in applications of tractable reasoning
  • Stefanie Speichert, interested in program induction
  • Andreas Bueff, interested in tractable learning
  • Himan Mookherjee (principal supervisor: James Cheney), interested in machine learning for anomaly detection
  • Samuel Kolb (KU Leuven, principal supervisor: Luc De Raedt), interested in machine learning for hybrid domains
  • Davide Nitti (PhD 2016, KU Leuven, principal supervisor: Luc De Raedt), interested in machine learning for hybrid domains

Bachelor and Master students:

  • Jazon Szabo (BSc, 2019), interested in probabilistic planning
  • Anton Fuxjaeger (BSc, 2018), interested in tractable reasoning
  • Oana Radu (BSc, 2018), interested in tractable reasoning
  • Michael Varley (MSc, 2018), interested in algorithmic fairness
  • Lewis Hammond (MSc, 2018), interested in responsible decision making
  • Laszlo Treszkai (MSc, 2018), interested in probabilistic planning
  • Amit Parag (MSc by Research, 2019), interested in machine learning for physics
  • Andreas Bueff (MSc by Research, 2018), interested in tractable learning
  • Rose Khan (MSc, 2017), interested in default reasoning
  • Nazgul Tazhigaliyeva (MSc, 2017), interested in model counting
  • Stefanie Speichert (MSc, 2017), interested in machine learning for hybrid domains

Visitors:

  • Yoram Moses, Technion
  • Brendan Juba, Washington University in St. Louis
  • Loizos Michael (via the Alan Turing Institute), Open University of Cyprus