Data for Evaluating Learning Valid Experiments: A standardized environment designed to evaluate the performance of methods that learn relationships based primarily on empirical data. Delve makes it possible for users to compare their learning methods ...

Learning and inference in complex probabilistic models.

Unsupervised learning, probabilistic density estimation, machine vision.

Unsupervised learning, machine learning, computational models of neural processing.

University of Toronto Computer Systems Research Group promotes research in the design, implementation, and operating characteristics of complex computing systems. Research and searchable database of technical reports.

Contestant and coach of prior programming contest teams in ACM Programming Contest regionals.