logo

dad and peterson Update: I have left MIT and joined Lyric Labs, an R&D group within Analog Devices, Inc. We'll be working on hardware accelerated Bayesian inference, probabilistic programming, and questions like "What is the GPU of machine learning?"

Formerly, I was a research scientist in the Computational Cognitive Science Group and Laboratory for Information and Decision Systems at MIT. I worked with Josh Tenenbaum, Leslie Kaelbling and Alan Willsky.

My research interests lie at the intersection of perception, control and learning. Specific interests include probabilistic programming, probabilistic modeling (particularly with structured Bayesian nonparametrics), reinforcement learning, dynamical systems modeling, information theory, manifold learning, kernel methods, massively parallel processing, visual perception, and optimal control. I dabble in robots as a side hobby.

Latest news:

I helped to organize a AAAI Spring Symposium called Designing Intelligent Robots: Reintegrating AI with George Konidaris, Sarah Osentoski, Todd Hester, Stephen Hart and Byron Boots. Check it out!

Our IJCAI 2011 paper, Bayesian Policy Search with Policy Priors won the Best Poster award!

Finale Doshi-Velez and I co-organized the ICML 2011 Workshop on Planning and Acting with Uncertain Models.

 
The top of a fluffy cloud.