My primary area of interest in research concerns computational theories of inference and learning in biological and artificial systems.
Questions that motivate me include: How can we construct artificial systems that analyze complex, cluttered environments with the ease and accuracy of natural systems? How can novel visual items be processed efficiently and how do representations and processing change as items become more familiar?
Recent Research Highlights
Leveraging user libraries to bootstrap collaborative filtering. Laurent Charlin, Richard Zemel, Hugo Larochelle. KDD 2014: 20th ACM Conference on Knowledge Discovery and Data Mining (2014). [pdf]
High order regularization for semi-supervised learning of structured output problems. Yujia Li, Richard Zemel. ICML-2014: The 31st International Conference on Machine Learning (2014). [pdf, poster, notes]
Input warping for Bayesian optimization of non-stationary functions. Jasper Snoek, Kevin Swersky, Richard Zemel, Ryan Adams. ICML-2014: The 31st International Conference on Machine Learning (2014). [pdf]
New learning methods for supervised and unsupervised preference aggregation. Maks Volkovs and Richard Zemel. JMLR: Journal of Machine Learning Research (2014). [pdf]
A multiplicative model for learning distributed text-based attribute representations. Ryan Kiros, Richard Zemel, Russ Salakhtudinov. ICML Workshop on Knowledge-Powered Deep Learning for Text Mining (2014). [pdf, web page]
Determinantal Point Process latent variable models for neural spiking data. Jasper Snoek, Ryan Adams, Richard Zemel. NIPS-2013: Advances in Neural Information Processing Systems. (2013). [pdf]
On the representational efficiency of Restricted Boltzmann Machines. James Martens, Arkadev Chattopadhyay, Toniann Pitassi, Richard Zemel. NIPS-2013: Advances in Neural Information Processing Systems (2013). [pdf]
Exploring compositional high order pattern potentials for structured output learning. Yujia Li, Daniel Tarlow, Richard Zemel. CVPR-2013: The 26th IEEE Conference on Computer Vision and Pattern Recognition (2013). [pdf, poster, notes]
The Toronto Paper Matching System: An automated paper-reviewer assignment system. Laurent Charlin and Richard Zemel. ICML Workshop on Peer Reviewing and Publishing Models (2013). [pdf]
Supervised CRF framework for preference aggregation. Maks Volkovs and Richard Zemel. CIKM-2013: International Conference on Information and Knowledge Management (2013). [pdf, code]
Stochastic k-neighborhood selection for supervised and unsupervised learning. Daniel Tarlow, Kevin Swersky, Laurent Charlin, Ilya Sutskever, Richard Zemel. . ICML-2013: The 30th International Conference on Machine Learning (2013). [pdf, notes]