Dr Peter SUNEHAG

Research Interests:

I am working on theoretical foundations for machine learning, in particular for universal reinforcement learning. I have also recently worked on stochastic approximation theory and on body-worn sensor analysis in a project with NICTA and the Australian Institute of Sports. Below follows some of my recent publications:

Semi-markov kmeans clustering and activity recognition from body-worn sensors M. Robards and P. Sunehag ICDM 2009

Variable Metrics Stochastic Approximation Theory P. Sunehag J. Trumpf, S.V.N. Vishwanathan and N. Scraudolph AISTATS 2009

Real method of interpolation on subcouples of codimension one (with S. Astashkin) Studia Math. 185 (2008), 151-168

Using two-stage word frequency models ... P. Sunehag AISTATS 2007

Bio:

I did my Ph.D. in theoretical mathematics at Uppsala University in Sweden. The topic of the thesis was interpolation of Banach spaces and Banach Algebras. I then worked at NICTA in Canberra Australia as a machine learning researcher. I worked with Document Analysis, Optimization and activity recognition from body-worn sensor. I am still involved in the last activity by being seconded to NICTA on a 20 percent basis.