Algebraic geometry of singular learning machines and symmetry of generalization and training errors

Neurocomputing

Volumn 67, Issue 1-4 SUPPL., 2005, Pages 198-213

  Watanabe, Sumio ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Algebraic geometry; Generalization error; Likelihood function; Resolution of singularities; Singular learning machines

Indexed keywords

ALGEBRA; COMPUTATIONAL GEOMETRY; ERROR ANALYSIS; HIERARCHICAL SYSTEMS; MATHEMATICAL MODELS; MAXIMUM LIKELIHOOD ESTIMATION; STATISTICAL METHODS;

LIKELIHOOD FUNCTIONS; STATISTICAL THEORY; TRAINING ERRORS;

LEARNING SYSTEMS;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL INTELLIGENCE; COMPUTER ANALYSIS; COMPUTER INTERFACE; COMPUTER PROGRAM; COMPUTER SIMULATION; GEOMETRY; HUMAN COMPUTER INTERACTION; INFORMATION PROCESSING; INFORMATION RETRIEVAL; LEARNING; MATHEMATICAL COMPUTING; MEDICAL INFORMATICS; METHODOLOGY; NERVE CELL NETWORK; PRIORITY JOURNAL; STATISTICAL ANALYSIS;

EID: 21744459329     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2004.11.037     Document Type: Article

References (16)

1. S. Amari, H. Park, T. Ozeki, Geometrical singularities in the neuromanifold of multilayer perceptrons, Adv. Neural Inform. Process. Systems 14 (2002) 343-350.
2. M.F. Atiyah Resolution of singularities and division of distributions Commun. Pure Appl. Math. 13 1970 145-150
3. D. Dacunha-Castelle E. Gassiat Testing in locally conic models, and application to mixture models Probab. Stat. 1 1997 285-317
4. K. Hagiwara On the problem in model selection of neural network regression in overrealizable scenario Neural Comput. 14 2002 1979-2002
5. J.A. Hartigan, A failure of likelihood asymptotics for normal mixtures, Proceedings of the Berkeley Conference in Honor of Jerzy Neyman and Jack Kiefer, vol. 2, 1985, pp. 807-810.
6. H. Hironaka Resolution of singularities of an algebraic variety over a field of characteristic zero Ann. Math. 79 1964 109-326
7. M. Kashiwara B-functions and holonomic systems Invent. Math. 38 1976 33-53
8. D. Rusakov, D. Geiger, Asymptotic model selection for naive Bayesian networks, Journal of Machine Learning Research 6 (1) (2005) 1-35.
9. A.W. van der Vaart J. Weller Weak Convergence and Empirical Processes 1996 Springer Berlin
10. S. Watanabe A generalized Bayesian framework for neural networks with singular Fisher information matrices Int. Symp. Nonlinear Theory Appl. 2 1995 207-210
11. S. Watanabe Algebraic analysis for singular statistical estimation Lect. Notes Comput. Sci. 1720 1999 39-50
12. S. Watanabe Algebraic analysis for non-regular learning machines Adv. Neural Inform. Process. 12 2000 356-362
13. S. Watanabe Algebraic analysis for non-identifiable learning machines Neural Comput. 13 4 2001 899-933
14. S. Watanabe Training and generalization errors of the hierarchical learning machines with algebraic singularities IEICE Trans. J84A 1 2001 99-108
15. S. Watanabe S.-I. Amari Learning coefficients of layered models when the true distribution mismatches the singularities Neural Comput. 15 5 2003 1013-1033
16. K. Yamazaki S. Watanabe Singularities in mixture models and upper bounds of stochastic complexity Int. J. Neural Networks 16 7 2003 1029-1038