Group’s contact person: Pascal Poupart

Group members



Machine learning is an area of specialization of statistics crossed with computer science, most notably with such areas as computational statistics, scientific computation, data visualization and computational complexity. We live in an era where information technologies allow individuals and large organizations to gather increasingly large volumes of data about business transactions, web click traces, health records, etc. This data contains a wealth of information; however, “mining” the data to extract relevant information is challenging. For instance, how can a fraud be identified from a stream of transactions, how can user preferences be inferred from click traces to improve web services, how can new health indices be designed based on logs of physiological measurements to better assess and monitor chronic diseases?

Research in machine learning is concerned largely with the analysis and development of algorithms to explore, discover, visualize and model structure in data as well as to make predictions and decisions based on that structure. Motivating data is often incomplete, noisy, nonhomogeneous in structure and large in size (e.g., large number of observations or dimensions, or both). Special attention is paid to the development of computationally efficient (with respect to time and memory usage) data analysis algorithms. Research includes the mathematical and computational analysis of the statistical methodology, the development of new methodologies, algorithms and software, and the application of these to substantive problems from other areas.

  • Topics of research: classification, regression, clustering, pattern analysis, structure discovery, feature extraction, dimensionality reduction, reasoning under uncertainty, decision making, data visualization, estimation, inference, prediction
  • Application areas: data mining, information retrieval, health informatics, bioinformatics, natural language processing, decision analysis, intelligent systems, computational finance.
  • Collaborations: Google, Intel, UW-Schlegel Research Institute in Aging, University Hospital (London, ON), Homewood Research Institute (Guelph), School of Public Health Sciences (University of Toronto), Sunnybrook Health Science Centre (Toronto), Alberta Ingenuity Centre for Machine Learning.