Algebraic Geometry and Statistical Learning Theory

Sure to be influential, Watanabe's book lays the foundations for the use of algebraic geometry in statistical learning theory. Many models/machines are singular: mixture models, neural networks, HMMs, Bayesian networks, stochastic context-free grammars are major examples. The theory achieved here underpins accurate estimation techniques in the presence of singularities.

Author: Sumio Watanabe
Publisher: Cambridge University Press
Published: 08/13/2009
Pages: 298
Binding Type: Hardcover
Weight: 1.20lbs
Size: 9.00h x 6.00w x 0.80d
ISBN: 9780521864671

About the Author
Watanabe, Sumio: - Sumio Watanabe is a Professor in the Precision and Intelligence Laboratory at the Tokyo Institute of Technology.