Electrical Engineering and Computer Science

Statistical Estimation and Learning

Research Areas -> Signal and Image Processing -> Statistical Estimation and Learning
 
Overview
Statistical learning extends the scope of signal processing beyond traditional waveform and image data to essentially any kind of quantitative measurement, such as gene expression intensities, Internet traffic volumes, and social networks. The emphasis is on large scale, complex, and potentially heterogeneous systems for which statistical models are not available a priori. Statistical learning instead seeks to learn models or decision rules from the data itself. Problem areas include classification or pattern recognition, clustering, anomaly detection, semi-supervised learning, dimensionality reduction, and dynamic Bayes networks.
 
Faculty
Balzano, Laura
Hero, Alfred O.
Lee, Honglak
Nadakuditi, Rajesh Rao
Scott, Clayton D


form photo