Research Assistant @ GRAAL Research Lab
Machine Learning Research Scientist
Pavillon Adrien-Pouliot, Office 3908
1065, avenue de la Médecine
Québec (Québec), Canada G1V 0A6
I seek learning algorithms that produce models that can be refined into knowledge that is valuable to domain experts.
- Phenotype prediction in genomics
- Learning sparse models on extremely high-dimensional data to correlate genomic variations with phenotypes. I collaborate to the development and maintenance of Kover, a tool allowing to learn interpretable computational phenotyping models from k-merized genomic data.
- Develop interpretable rule-based machine learning algorithms
- Develop learning algorithms based on sample-compression theory and take advantage of statistical bounds during the learning phase.
- Interpretable Deep Neural Networks
- Attention Mechanisms
- Reinforcement Learning
Conferences and Workshops
Drouin, A., Raymond, F., Letarte St-Pierre, G., Marchand, M., Corbeil, J. & Laviolette, F. (2016). Large scale modeling of antimicrobial resistance with interpretable classifiers. Machine Learning for Health Workshop, NIPS, Barcelona, Spain. [ pdf ]