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?

A flexible generative model for preference aggregation. Maksims Volkovs and Richard Zemel. WWW 2012: 21st International World Wide Web Conference (2012). [pdf]

Structured output learning with high order loss functoins. Daniel Tarlow and Richard Zemel. AIStats-2012: Fifteenth International Conference on Artificial Intelligence and Statistics (2012). [pdf]

Randomized optimum models for structured prediction. Daniel Tarlow, Ryan Adams, and Richard Zemel. AIStats-2012: Fifteenth International Conference on Artificial Intelligence and Statistics (2012). [pdf]

Fairness through awareness. Cynthia Dwork, Moritz Hardt, Toniann Pitassi, Omer Reingold, Richard Zemel. Proceedings of Innovations of Theoretical Computer Science (2012). [pdf]

Dynamic cue combination in distributional population code networks. Rama Natarajan and Richard Zemel. Sensory Cue Integration, Oxford University Press (2011). [pdf]

Graph cuts is a max-product algorithm. Daniel Tarlow, Inmar Givoni, Richard Zemel, & Brendan Frey. UAI 2011: 27th Conference on Uncertainty in Artificial Intelligence (2011). [pdf]

A framework for optimizing paper matching. Laurent Charlin, Richard Zemel, & Craig Boutilier. UAI 2011: 27th Conference on Uncertainty in Artificial Intelligence (2011). [pdf]

Recommender systems: Missing data and statistical model estimation. Benjamin Marlin, Richard Zemel, Sam Roweis, & Malcolm Slaney. IJCAI: 22nd International Joint Conference on Artificial Intelligence (2011). [pdf]

BoltzRank: Learning to maximize expected ranking gain. Maksims Volkovs and Richard Zemel. ICML-2009: International Conference on Machine Learning (2009). [pdf]

HOP-MAP: Efficient message-passing with Higher-Order Potentials. Daniel Tarlow, Inmar Givoni, and Richard Zemel. AISTATS-2010: The 13th International Conference on Artificial Intelligence and Statistics (2010). [pdf, code, poster]

Learning articulated structure and motion. David Ross, Daniel Tarlow, and Richard Zemel. International Journal on Computer Vision (2010). [pdf, video, web page]

Collaborative prediction and ranking with non-random missing data. Ben Marlin and Richard Zemel. Recsys-2009: ACM Conference on Recommender Systems (2009). [pdf]

Characterizing response behavior in multi-sensory perception with conflicting cues. Rama Natarajan, Iain Murray, Ladan Shams, and Richard Zemel. NIPS-2008: Advances in Neural Information Processing Systems (2008). [pdf]

Learning hybrid models for image annotation with partially labeled data. Xuming He and Richard Zemel. NIPS-2008: Advances in Neural Information Processing Systems (2008). [pdf]

Generative versus discriminative training of RBMs for classification of fMRI images. Tanya Schmah, Geoffrey Hinton, Richard Zemel, Steven Small and Stephen Strother. NIPS-2008: Advances in Neural Information Processing Systems (2008). [pdf]

Unsupervised learning of skeletons from motion. David Ross, Daniel Tarlow, and Richard Zemel. ECCV-2008: European Conference on Computer Vision (2008). [pdf]

Flexible priors for exemplar-based clustering. Daniel Tarlow, Richard Zemel, and Brendan Frey. UAI-2008: The 24th Conference on Uncertainty in Artificial Intelligence (2008). [pdf]

Latent topic random fields: Learning using a taxonomy of labels. Xuming He and Richard Zemel. CVPR-2008: IEEE Conference on Computer Vision and Pattern Recognition (2008). [pdf]

Learning stick-figure models using nonparametric Bayesian priors over trees. Ted Meeds, David Ross, Richard Zemel, and Sam Roweis. CVPR-2008: IEEE Conference on Computer Vision and Pattern Recognition (2008). [pdf]

Encoding and decoding spikes for dynamic stimuli. Rama Natarajan, Quentin Huys, Peter Dayan, and Richard Zemel. Neural Computation, 20(9): 2325-2360 (2008). [pdf]

Learning flexible features for conditional random fields. Liam Stewart, Xuming He, and Richard Zemel. IEEE Transactions on Pattern Analysis and Machine Intelligence (2008). [pdf]