I am currently a Computer Science PhD student at UC Berkeley focusing on statistical machine learning in the "Statistical Artificial Intelligence Lab" (SAIL) lead by Michael Jordan. Previously, I was in the "Stanford AI Lab" (also SAIL) where I completed an MS Computer Science as well as a BS Mathematics and BA Spanish.
During the 2008-2009 and 2009-2010 academic years, I am co-organizing the
Machine Learning Tea
at Berkeley.
Research
-
Nonparametric Latent Feature Models for Link Prediction.
Kurt T. Miller, Thomas L. Griffiths, and Michael I. Jordan.
Advances in Neural Information Processing Systems (NIPS) 23, 2009. -
Continuous Time Group Discovery in Dynamic Graphs.
Kurt T. Miller and Tina Eliassi-Rad.
Analyzing Networks and Learning with Graphs Workshop at NIPS, 2009. -
Latent Feature Models for Link Prediction.
Kurt T. Miller, Thomas L. Griffiths, and Michael I. Jordan.
Snowbird Machine Learning Workshop, 2009. -
Variational Inference for the Indian Buffet Process.
Finale Doshi-Velez, Kurt T. Miller, Jurgen Van Gael and Yee Whye Teh.
Conference on Artificial Intelligence and Statistics (AISTATS), 2009.
Long version with all the derivations.
Matlab code for the linear-Gaussian model. -
Variations on Non-Exchangeable Nonparametric Priors for Latent Feature Models.
Kurt T. Miller, Thomas L. Griffiths, and Michael I. Jordan.
Nonparametric Bayes Workshop at ICML/UAI, 2008. -
The Phylogenetic Indian Buffet Process: A Non-Exchangeable Nonparametric Prior for Latent Features.
Kurt T. Miller, Thomas L. Griffiths and Michael I. Jordan.
Conference on Uncertainty in Artificial Intelligence (UAI), 2008.
-
Optic Flow Sensors for MAV (Micro Air Vehicle) Navigation.
Geoffrey L. Barrows, Craig Neely and Kurt T. Miller.
Chapter 26 in Fixed and Flapping Wing Aerodynamics for Micro Air Vehicle Applications, T.J. Mueller, Ed.
American Institute of Aeronautics and Astronautics (AIAA), 2001. -
Fusing Neuromorphic Motion Detector Outputs for Robust Optic Flow Measurement.
Geoffrey L. Barrows, Kurt T. Miller and Brian Krantz.
International Joint Conference on Neural Networks (IJCNN), 1999. -
Feature Tracking Linear Optic Flow Sensor Chip.
Kurt T. Miller and Geoffrey L. Barrows.
International Symposium on Circuits and Systems (ISCAS), 1999.
JET Program
I spent 2003-2004 teaching English in Japan through the JET Program. I have posted some photos, but there are intentionally few pictures of people (including me) available to the public in this album. Feel free to get in touch with me if you are interested in learning more about the JET Program.
Miscellaneous
- LaTeX poster template. This template makes posters that look like this. Feel free to use and distribute this template. There is probably a lot of room for improvement, so please let me know (e-mail address below) if you have any suggestions or to let me know you have used it and found it helpful. Posters using an earlier version of it have already appeared in multiple machine learning conferences.
- A mini-guide for getting set up with Hadoop for machine learning people at Berkeley that I helped put together. We have provided sample code for how to do logistic regression with Hadoop.
