Machine Learning and Artificial Intelligence

Figure : Sports sciences through data sciences (Louvain-la-Neuve Running Heatmap)

ICTEAM research activities in this field are conducted by ten primary investigators and about fourty researchers. There are two main domains of activity : Machine Learning and Constraint Programming.

Principal Investigators :

Martin Andraud, Pierre-Antoine Absil, Jean-Charles Delvenne, Yves Deville, Pierre Dupont, John Lee, Estelle Massart, Siegfried Nijssen, Eric Piette, Marco Saerens, Pierre Schaus, Michel Verleysen

Research Labs :

Machine Learning Group, Constraint Group

Research areas :

The research carried out by the UCLouvain Machine Learning Group (MLG) covers both fundamental and applied aspects of machine learning.

Machine learning aims at mining large collection of data and at building models to predict future data. This multidisciplinary field has links to statistics, signal processing, information theory and optimization. It also covers a wide range of applications such as biomedical data analysis, image and video analysis, time series prediction, graph mining, natural language processing, ...

The group specifically addresses the following topics:

  • High-dimensional, functional and non-linear data analysis
  • Feature and model selection
  • Data visualization and manifold learning
  • Bayesian learning
  • Biomedical signal processing and analysis, including ECG, EEG, and respiratory signal analysis, and medical image filtering
  • High-throughput biological data analysis, including microarray data analysis and next-generation sequencing
  • Temporal series prediction, including electrical workload prediction, financial time-series forecasting, networking measurement prediction
  • Automata and Grammar induction with application to software system modeling
  • Structured data analysis, graph mining and collaborative filtering

The UCL Machine Learning Group is organizing, on a yearly basis since 1993, the European Symposium on Artificial Neural Networks - Advances in Computational Intelligence and Learning

Constraint Programming (CP) is a powerful paradigm for modelling and solving complex combinatorial (optimization) problems. It integrates techniques from artificial intelligence, computer science, operational research and optimization. CP separates the modelling of the problem from the search for solutions. It offers high level modelling languages based on constraints. CP proposes two complementary search mechanisms. Standard CP is based on systematic tree search coupled with pruning techniques to remove infeasable solutions. Constraint-Based Local Search (CBLS) allows heuristic search based on the exploration of neighborhoods. The Constraint Group is mainly interested in consistency techniques, integration of CP and CBLS, graph matching, routing problems, applications in networking, ...

Most recent publications

Below are listed the 10 most recent journal articles and conference papers produced in this research area. You also can access all publications by following this link : see all publications.

Journal Articles

1. Piette, Eric; Crist, Walter; Soemers, Dennis J.N.J.; Rougetet, Lisa; Courts, Summer; Penn, Tim; Morenville, Achille. GameTable COST action: kickoff report. In: ICGA Journal, Vol. 45, no. 4, p. 1-17 (2024). doi:10.3233/icg-240245.

2. Dennis J.N.J. Soemers; Mella Vegard; Piette, Eric; Matthew Stephenson; Cameron Browne; Olivier Teytaud. Towards a General Transfer Approach for Policy-Value Networks. In: Transactions on Machine Learning Research, (2023).

3. Vermeylen, Charlotte; Olikier, Guillaume; Absil, Pierre-Antoine; Van Barel, Marc. Rank Estimation for Third-Order Tensor Completion in the Tensor-Train Format. In: Proceedings of the 31st European Signal Processing Conference (EUSIPCO 2023, , p. 965-969 (2023). doi:10.48550/arXiv.2309.15170.

4. van den Elzen, Stef; Andrienko, Gennady; Andrienko, Natalia; Fisher, Brian D; Martins, Rafael M; Peltonen, Jaakko; Telea, Alexandru C; Verleysen, Michel. The Flow of Trust: A Visualization Framework to Externalize, Explore, and Explain Trust in ML Applications. In: IEEE Computer Graphics and Applications, Vol. 43, no.2, p. 78-88 (2023).

5. Piette, Eric; Soemers, Dennis J.N.J.; Stephenson, Matthew; Browne, Cameron. The 2022 Ludii AI competition. In: ICGA Journal, Vol. 45, no.1, p. 16-27 (2023). doi:10.3233/icg-230230.

6. Soemers, Dennis J.N.J.; Samothrakis, Spyridon; Piette, Eric; Stephenson, Matthew. Extracting tactics learned from self-play in general games. In: Information Sciences, Vol. 624, no. 1, p. 277-298 (2023). doi:10.1016/j.ins.2022.12.080.

7. Soemers, Dennis J.N.J.; Piette, Eric; Stephenson, Matthew; Browne, Cameron. Spatial state-action features for general games. In: Artificial Intelligence, Vol. 321, no. 103937, p. 32 (2023). doi:10.1016/j.artint.2023.103937.

8. Browne, Cameron; Piette, Eric; Crist, Walter; Stephenson, Matthew; Soemers, Dennis. Report on the 2nd Digital Ludeme Project Workshop. In: ICGA Journal, Vol. 44, no. 2, p. 56-66 (2022). doi:10.3233/icg-220211.

9. Dirksen, Sjoerd; Genzel, Martin; Stollenwerk, Alexander; Jacques, Laurent. The Separation Capacity of Random Neural Networks. In: Journal of Machine Learning Research, Vol. 23, no.209, p. 1--47 (2022). (Accepté/Sous presse).

10. Olikier, Guillaume; Absil, Pierre-Antoine. On the Continuity of the Tangent Cone to the Determinantal Variety. In: Set-Valued and Variational Analysis, Vol. 30, p. 769-788 (2022). doi:10.1007/s11228-022-00629-0.

Conference Papers

1. Morenville, Achille; Piette, Eric. Vers une Approche Polyvalente pour les Jeux à Information Imparfaite sans Connaissance de Domaine. 2024 xxx.

2. Langlois, Quentin; Szelagowski, Nicolas; Vanderdonckt, Jean; Jodogne, Sébastien. Open Platform for the De-identification of Burned-in Texts in Medical Images using Deep Learning. In: Proc. of the 17th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2024). Vol. 1, p. 297-304 (2024). SCITEPRESS – Science and Technology Publications, Lda. 2024 xxx. doi:10.5220/0012430300003657.

3. Vermeylen, Charlotte; Olikier, Guillaume; Van Barel, Marc. An Approximate Projection onto the Tangent Cone to the Variety of Third-Order Tensors of Bounded Tensor-Train Rank. In: Lecture Notes in Computer Science : Geometric Science of Information, volume14071, Springer Nature Switzerland: Switzerland, 2023, 9783031382703, p. 484-493 xxx. doi:10.1007/978-3-031-38271-0_48.

4. Danhier, Martin; El Khoury, Karim; Macq, Benoît. An open-source fine-grained benchmarking platform for wireless virtual reality. 2023 xxx.

5. Fierens, Amaury; Jodogne, Sébastien. BERTinchamps: Cost-Effective Training of Large Language Models for Medical Tasks in French. In: CEUR Workshop Proceedings. Vol. 3551 (2023). CEUR Workshop Proceedings, 2023 xxx.

6. Langlois, Quentin; Jodogne, Sébastien. Practical Study of Deep Learning Models for Speech Synthesis. In: Proceedings of the 16th International Conference on PErvasive Technologies Related to Assistive Environments (PETRA '23), Association for Computing Machinery: New York, NY, USA, 2023, 979-8-4007-0069-9, p. 700–706 xxx. doi:10.1145/3594806.3596536.

7. Jodogne, Sébastien. Client-Side Application of Deep Learning Models Through Teleradiology. In: Studies in Health Technology and Informatics. Vol. 302, no.1, p. 997-1001 (2023). Maria Hägglund et al. 2023 xxx. doi:10.3233/shti230325.

8. Stephenson, Matthew; Soemers, Dennis; Piette, Eric; Browne, Cameron. Measuring Board Game Distance. In: Computers and Games : Lecture Notes in Computer Science, 2022, 9783031340161, p. 121-130 xxx. doi:10.1007/978-3-031-34017-8_11.

9. Gerniers, Alexander; Dupont, Pierre. MicroCellClust 2: a hybrid approach for multivariate rare cell mining in large-scale single-cell data. In: 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2022, 978-1-6654-6819-0, p. 148-153 xxx. doi:10.1109/bibm55620.2022.9995176.

10. Soemers, Dennis; Piette, Eric; Stephenson, Matthew; Browne, Cameron. Optimised Playout Implementations for the Ludii General Game System. In: Advances in Computer Games: 17th International Conference, 2021, 9783031114878 xxx.