Algebraic Geometry and Statistical Learning Theory

Nonfiction, Computers, Advanced Computing, Engineering, Computer Vision, Science & Nature, Mathematics, General Computing
Cover of the book Algebraic Geometry and Statistical Learning Theory by Sumio Watanabe, Cambridge University Press
View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart
Author: Sumio Watanabe ISBN: 9781107713963
Publisher: Cambridge University Press Publication: August 13, 2009
Imprint: Cambridge University Press Language: English
Author: Sumio Watanabe
ISBN: 9781107713963
Publisher: Cambridge University Press
Publication: August 13, 2009
Imprint: Cambridge University Press
Language: English

Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory on algebraic varieties.

View on Amazon View on AbeBooks View on Kobo View on B.Depository View on eBay View on Walmart

Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models and learning machines applied to information science have a parameter space that is singular: mixture models, neural networks, HMMs, Bayesian networks, and stochastic context-free grammars are major examples. Algebraic geometry and singularity theory provide the necessary tools for studying such non-smooth models. Four main formulas are established: 1. the log likelihood function can be given a common standard form using resolution of singularities, even applied to more complex models; 2. the asymptotic behaviour of the marginal likelihood or 'the evidence' is derived based on zeta function theory; 3. new methods are derived to estimate the generalization errors in Bayes and Gibbs estimations from training errors; 4. the generalization errors of maximum likelihood and a posteriori methods are clarified by empirical process theory on algebraic varieties.

More books from Cambridge University Press

Cover of the book Incivility by Sumio Watanabe
Cover of the book The Holy City of Medina by Sumio Watanabe
Cover of the book Idealism beyond Borders by Sumio Watanabe
Cover of the book Candidates and Voters by Sumio Watanabe
Cover of the book Subjectivity in the Twenty-First Century by Sumio Watanabe
Cover of the book The Cambridge Companion to Christian Doctrine by Sumio Watanabe
Cover of the book Horace: Odes Book II by Sumio Watanabe
Cover of the book Authority by Sumio Watanabe
Cover of the book WCDMA Design Handbook by Sumio Watanabe
Cover of the book Religion and the Political Imagination by Sumio Watanabe
Cover of the book India before Europe by Sumio Watanabe
Cover of the book Dynamics of Particles and Rigid Bodies by Sumio Watanabe
Cover of the book The Cambridge Companion to John Dryden by Sumio Watanabe
Cover of the book Jonathan Swift and the Eighteenth-Century Book by Sumio Watanabe
Cover of the book Search User Interfaces by Sumio Watanabe
We use our own "cookies" and third party cookies to improve services and to see statistical information. By using this website, you agree to our Privacy Policy