MATRIX METHODS IN DATA MINING AND PATTERN RECOGNITION

Catalog description

This course focuses on matrix methods in data mining and pattern recognition, and features real-world applications ranging from classification and clustering to denoising and data analysis. The topics covered include: linear equations, regression, regularization, the singular value decomposition, iterative algorithms, classification using singular value decomposition bases, tangent distance, latent semantic indexing, clustering, support vector machines, and random walk and Markov chains. PREREQ: ADMISSION TO GRADUATE PROGRAM IN COMPUTER SCIENCE