Research

Interests

I'm interested in statistical machine learning and probabilistic models of human cognition. My long-term goal is to build intelligent computer programs that are inspired by human neurobiology and psychology.

Peer-reviewed publications

Thomas L. Griffiths, Adam N. Sanborn, Kevin R. Canini, and Daniel J. Navarro, "Categorization as nonparametric Bayesian density estimation", M. Oaksford and N. Chater (Eds.), The probabilistic mind: Prospects for rational models of cognition, Oxford: Oxford University Press. March 2007. (pdf)

Thomas L. Griffiths, Kevin R. Canini, Adam N. Sanborn, and Daniel J. Navarro, "Unifying Rational Models of Categorization via the Hierarchical Dirichlet Process", 29th Annual Conference of the Cognitive Science Society, February 2007. (pdf)

Other papers

Master's project report: Kevin R. Canini, "Modeling Categorization as a Dirichlet Process Mixture", EECS Department, University of California, Berkeley, Tech. Rep. UCB/EECS-2007-69, May 2007. (available online)

Jacob Abernethy, Kevin Canini, John Langford, and Alex Simma, "Online Collaborative Filtering", February 2007. (pdf)

Peter Bodík, Michael Armbrust, Kevin Canini, Armando Fox, Michael Jordan, and David Patterson, "A Case For Adaptive Datacenters To Conserve Energy and Improve Reliability", January 2007. (pdf)


Projects

Human Categorization Modeling

We are exploring Dirichlet Process Mixture Models as a way to explain human performance on categorization tasks. Our model can be viewed as interpolating between the traditional exemplar and prototype models.

Colleagues

Online Gradient Descent

We are attempting to use online gradient descent methods to find low-rank approximations to very large, sparsely-observed matrices. One application for this is the Netflix Prize.

Colleagues

DRAPE

Dynamic Resource Allocation for Power Efficiency is an investigation of various methods for conserving power in large data centers. Our initial prototype was a system that uses a predicted workload to turn servers on and off while replaying traces from the 1998 World Cup website. Our project report is available online.

Colleagues

Undergraduate Research