Algebraic Geometry and Statistical Learning Theory (Hardcover)

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.

General

Imprint:	Cambridge UniversityPress
Country of origin:	United Kingdom
Series:	Cambridge Monographs on Applied and Computational Mathematics
Release date:	August 2009
First published:	August 2009
Authors:	Sumio Watanabe
Dimensions:	235 x 155 x 20mm (L x W x T)
Format:	Hardcover
Pages:	286
ISBN-13:	978-0-521-86467-1
Categories:	Books > Science & Mathematics > Mathematics > Geometry > Algebraic geometry Books > Computing & IT > Applications of computing > Artificial intelligence > Machine learning Promotions
LSN:	0-521-86467-4
Barcode:	9780521864671

Is the information for this product incomplete, wrong or inappropriate? Let us know about it.

Does this product have an incorrect or missing image? Send us a new image.

Is this product missing categories? Add more categories.

Review This Product

No reviews yet - be the first to create one!