Generalized Principal Component Analysis

The main goal of this book is to introduce a new method to study hybrid models, referred to as generalized principal component analysis. The general problems that GPCA aims to address represents a fairly general class of unsupervised learning problems— many data clustering and modeling methods in machine learning can be viewed as special cases of this method. This book provides a comprehensive introduction of the fundamental statistical, geometric and algebraic concepts associated with the estimation (and segmentation) of the hybrid models, especially the hybrid linear models.

Rene Vidal is a Professor of Biomedical Engineering and Director of the Vision Dynamics and Learning Lab at The Johns Hopkins University.

S. Shankar Sastry is Dean of the College of Engineering, Professor of Electrical Engineering and Computer Science and Professor of Bioengineering at the University of California, Berkeley.