Algebraic geometrical methods for hierarchical learning machines

Neural Networks

Volumn 14, Issue 8, 2001, Pages 1049-1060

  Watanabe, Sumio ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Algebraic geometry; Asymptotic expansion; Generalization error; Non identifiable model; Resolution of singularities; Stochastic complexity

Indexed keywords

ALGORITHMS; GEOMETRY; MATRIX ALGEBRA; PROBABILITY DISTRIBUTIONS; RADIAL BASIS FUNCTION NETWORKS;

HIERARCHICAL LEARNING MACHINES;

LEARNING SYSTEMS;

ALGORITHM; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; GEOMETRY; LEARNING; MATHEMATICAL ANALYSIS; PRIORITY JOURNAL; STATISTICAL ANALYSIS; STATISTICS; STOCHASTIC MODEL; TECHNOLOGY;

EID: 0034842476     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(01)00069-7     Document Type: Article

References (39)

1. Likelihood and Bayes procedures
2. A universal theorem on learning curves
3. Statistical theory of learning curves under entropic loss
4. Differential and algebraic geometry of multilayer perceptrons
5. Four types of learning curves
6. Resolution of singularities and division of distributions
7. Approximation and estimation bounds for artificial neural networks
8. The analytic continuation of generalized functions with respect to a parameter
9. Testing in locally conic models, and application to mixture models
10. A regularity condition of information matrix of a multilayer perceptron network
11. On the problem of applying AIC to determine the structure of a layered feed-forward neural network
12. A failure of likelihood asymptotics for normal mixtures
13. Mutual information, metric entropy and cumulative relative entropy risk
14. Resolution of singularities of an algebraic variety over a field of characteristic zero
15. B-functions and holonomic systems
16. A statistical approach to learning and generalization in layered neural networks
17. Bayesian interpolation
18. On the stochastic complexity of learning realizable and unrealizable rules
19. An integral representation with ridge functions and approximation bounds of three-layered network
20. Bounds for predictive errors in the statistical mechanics of supervised learning
21. Stochastic complexity and modeling
22. On zeta functions associated with prehomogeneous vector space
23. Estimating the dimension of a model
24. On the essential difference between neural networks and regular statistical models
25. On the generalization error by a layered statistical model with Bayesian estimation
26. Learning efficiency of redundant neural networks in Bayesian estimation
27. Algebraic analysis for singular statistical estimation
28. Algebraic analysis for non-regular learning machines
29. Algebraic analysis for non-identifiable learning machines
30. Training and generalization errors of the hierarchical learning machines with algebraic singularities
31. Algebraic information geometry for learning machines with singularities
32. Probabilistic design of layered neural networks based on their unified framework
33. Learning in artificial neural networks: A statistical perspective
34. A decision-theoretic extension of stochastic complexity and its applications to learning