Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory.
"synopsis" may belong to another edition of this title.
Sumio Watanabe is a Professor in the Precision and Intelligence Laboratory at the Tokyo Institute of Technology.
"About this title" may belong to another edition of this title.
Seller: Books From California, Simi Valley, CA, U.S.A.
hardcover. Condition: Good. Seller Inventory # mon0003879521
Seller: Books From California, Simi Valley, CA, U.S.A.
hardcover. Condition: Very Good. Seller Inventory # mon0003745054
Seller: thebookforest.com, San Rafael, CA, U.S.A.
Condition: Like New. hardcover. Text block firm and clean, binding unblemished, boards straight, without highlights or underlining. Fine, like new condition. Supporting Bay Area Friends of the Library since 2010. Well packaged and promptly shipped. Seller Inventory # BAY04-00026
Seller: Lucky's Textbooks, Dallas, TX, U.S.A.
Condition: New. Seller Inventory # ABLIING23Feb2416190019109
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: New. Seller Inventory # 6165683-n
Seller: California Books, Miami, FL, U.S.A.
Condition: New. Seller Inventory # I-9780521864671
Seller: Ria Christie Collections, Uxbridge, United Kingdom
Condition: New. In. Seller Inventory # ria9780521864671_new
Quantity: Over 20 available
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: As New. Unread book in perfect condition. Seller Inventory # 6165683
Seller: Grand Eagle Retail, Bensenville, IL, U.S.A.
Hardcover. Condition: new. 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. Sure to be influential, this book lays the foundations for the use of algebraic geometry in statistical learning theory. Many widely used statistical models are singular: mixture models, neural networks, HMMs, and Bayesian networks are major examples. The theory achieved here underpins accurate estimation techniques in the presence of singularities. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Seller Inventory # 9780521864671
Seller: GreatBookPricesUK, Woodford Green, United Kingdom
Condition: New. Seller Inventory # 6165683-n
Quantity: Over 20 available