Spring 2017: 550.735 TOPICS IN STATISTICAL PATTERN RECOGNITION

MW @ 4:30-5:45 @ Gilman 75
Prof. Carey E. Priebe
Department of Applied Mathematics and Statistics
Johns Hopkins University

“Statistical pattern recognition” is my version of an explicitly prob/stat-centric “machine learning” or “data mining” course, following naturally from 550.630. We focus on theoretical and practical issues in statistical pattern recognition. We prove theorems, including universal consistency and arbitrarily poor performance. Both the theory and the practice of classification & clustering are stressed. Real problems and data will be considered throughout.

I will be teaching out of DGL == Devroye, Gyorfi and Lugosi, A Probabilistic Approach to Pattern Recognition, 1996. 

Student interest will contribute to topic selection.

• prereqs are prob & stat at the 400 level.
• prob & stat at the 600 level, and stat pat rec at the Duda&Hart level, would be helpful but are not required.