Gianluca Bontempi is professor of modelling, bioinformatics and machine learning in the Computer Science Department of the ULB Faculty of Sciences. In 2004 he founded the ULB Machine Learning Group (mlg.ulb.ac.be) and in 2013 he has been appointed Director of the newly created interdisciplinary Institute for Bioinformatics in Brussels. The group currently includes 3 permanent members (Gianluca Bontempi, Tom Lenaerts and Maarten Jansen), 6 postdocs and 11 PhD researchers. The research of the group covers the areas of machine learning, computational modelling and statistics and their applications to problems of data mining, bioinformatics, simulation and time series prediction. In particular three main topics are addressed:
1. Data mining of massive datasets: this research concerns the design and application of machine learning techniques for extracting relevant information from real massive datasets. A particular attention is devoted to techniques of feature selection, causal inference, model selection and validation and long-term prediction. Several real applications have been targeted (wireless sensor networks, text mining, biomedical applications, finance, fraud detection, geographical data analysis, spatio-temporal forecasting).
2. Bioinformatics and computational biology: this research addresses the use of computational techniques for the modelling, simulation and prediction of complex biological systems. In this context the research of Gianluca Bontempi focuses on the use of machine learning techniques for the classification of microarray data in breast cancer and diabetes and the inference of genomic networks. The research of Tom Lenaerts aims to identify and analyse the information processing capacity of proteins and to understand the dynamics of chronic myeloid leukaemia (CML).
3. Evolutionary game theory: this research investigates the evolution of cooperation (coordination), the role of complex networks in this process and the relations with individual learning. In this context, Tom Lenaerts provided substantial contributions to the effect of network structure on the evolution and learning of cooperative behaviour.