I am interested in machine learning algorithms for information visualisation, as well as related questions in other fields of computer science. Also, I am interested in the interpretability of models (i.e. what makes a model interpretable and how can we make it more interpretable). These two questions are ubiquitous in modern data analysis.
As such, I am chair/organiser for the special session “Information Visualisation and Machine Learning: Techniques, Validation and Integration” at the ESANN 2016 conference.
- Benoît Frénay and Bruno Dumas. Information Visualisation and Machine Learning: Characteristics, Convergence and Perspective. In Proc. ESANN, Bruges, Belgium, 27-29 April 2016, p. 623-628.
- Adrien Bibal and Benoît Frénay. Interpretability of Machine Learning Models and Representations: an Introduction. In Proc. ESANN, Bruges, Belgium, 27-29 April 2016, p. 77-82.
- Frénay, B., Hofmann, D., Schulz, A., Biehl, M., Hammer, B. Valid Interpretation of Feature Relevance for Linear Data Mappings. In Proc. IEEE CIDM, Orlando, Florida, USA, 9-12 December 2014, p. 149–156.