Erik G. Learned-Miller

248 CS Building
(413) 545-2993


Computer vision and machine learning. Probabilistic and statistical methods in vision and image processing. Non-parametric statistics. Information theoretic methods. Unsupervised and semi-supervised learning.


Professor Learned-Miller's interests can be broadly categorized as applying ideas and methods from machine learning to problems in computer vision. Problems he has worked on include learning from a small number of examples, independent components analysis, color constancy, the modeling of shape deformations, and mathematical expression recognition. His Ph.D. thesis focuses on using learned statistical knowledge from one visual task to speed learning of a new, related task. More recently his work has focused on face recognition, scene text recognition, and low-level image matching problems.


Ph.D., Electrical Engineering and Computer Science, Massachusetts Institute of Technology (2002), M.S., Electrical Engineering and Computer Science, Massachusetts Institute of Technology (1997), B.A., Psychology, Yale University (1988). Professor Learned-Miller joined the faculty in the University of Massachusetts Amherst College of Information and Computer Sciences in 2004 as an Assistant Professor. His most recent position was a post-doctoral research engineer in the Electronics Research Laboratory at the University of California, Berkeley. Previously, Professor Learned-Miller was the Chief Executive Officer and co-founder of CORITechs, Inc., a company that designed surgical planning software for neurosurgeons.

Activities & Awards

Professor Learned-Miller received the Microsoft-MIT graduate student fellowship. He holds a patent for "apparatus for neurosurgical stereotactic procedures." Professor Learned-Miller is on the editorial board of the Journal of Machine Learning Research. He received an NSF CAREER Award in 2006. He will be a co-program chair for Computer Vision and Pattern Recognition in 2015.