Algebraic geometry and statistical learning theory [E-Book] / Sumio Watanabe.
Watanabe, Sumio, (author)
Cambridge : Cambridge University Press, 2009
1 online resource (viii, 286 pages)
englisch
9780521864671
9780511800474
Cambridge monographs on applied and computational mathematics ; 25
Full Text
LEADER 02161nam a22003138i 4500
001 CR9780511800474
003 UkCbUP
008 101021s2009||||enk o ||1 0|eng|d
020 |a 9780511800474 
020 |a 9780521864671 
035 |a (Sirsi) a792373 
041 |a eng 
082 0 0 |a 006.3/1  |2 22 
100 1 |a Watanabe, Sumio,  |e author 
245 1 0 |a Algebraic geometry and statistical learning theory  |h [E-Book] /  |c Sumio Watanabe. 
264 1 |a Cambridge :  |b Cambridge University Press,  |c 2009  |e (CUP)  |f CUP20200108 
300 |a 1 online resource (viii, 286 pages) 
336 |a text  |b txt  |2 rdacontent 
337 |a computer  |b c  |2 rdamedia 
338 |a online resource  |b cr  |2 rdacarrier 
490 |a Cambridge monographs on applied and computational mathematics ;  |v 25 
500 |a englisch 
520 |a 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. 
650 0 |a Computational learning theory  |x Statistical methods. 
650 0 |a Geometry, Algebraic. 
856 4 0 |u https://doi.org/10.1017/CBO9780511800474  |z Volltext 
932 |a CambridgeCore (Order 30059) 
596 |a 1 
949 |a XX(792373.1)  |w AUTO  |c 1  |i 792373-1001  |l ELECTRONIC  |m ZB  |r N  |s Y  |t E-BOOK  |u 8/1/2020  |x UNKNOWN  |z UNKNOWN  |1 ONLINE