Learning efficiency of redundant neural networks in Bayesian estimation

IEEE Transactions on Neural Networks

Volumn 12, Issue 6, 2001, Pages 1475-1486

  Watanabe, S ^a  

^a TOKYO INSTITUTE OF TECHNOLOGY   (Japan)

Author keywords

Bayesian learning; Free energy; Generalization error; Kullback information; Nonidentifiable model

Indexed keywords

ASYMPTOTIC STABILITY; COMPUTATIONAL COMPLEXITY; ESTIMATION; LEARNING ALGORITHMS; MATHEMATICAL MODELS; PROBABILITY DISTRIBUTIONS; RANDOM PROCESSES; STATISTICAL METHODS;

BAYESIAN ESTIMATION; BAYESIAN LEARNING; GENERALIZATION ERROR; KULLBACK INFORMATION; REDUNDANT NEURAL NETWORKS; STOCHASTIC COMPLEXITY;

MULTILAYER NEURAL NETWORKS;

EID: 0035506030     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.963783     Document Type: Article

References (32)

1. A new look at the statistical model identification
2. Likelihood and Bayes procedure
3. Neural Comput.
4. Robust full Bayesian learning machines for neural networks
5. Approximation and estimation bounds for artificial neural networks
6. A regularity condition of the information matrix of a multilayer perceptron network
7. Generalization error of linear neural networks in unidentifiable cases
8. On the problem of applying AIC to determine the structure of a layered feedforward neural network
9. The determination of the order of an autoregression
10. A failure of likelihood asymptotics for normal mixtures
11. Bayesian radial basis functions of variable dimension
12. A statistical approaches to learning and generalization in layered neural networks
13. Bayesian interpolation
14. Neural networks for optimal approximation of smooth and analytic functions
15. Network information criterion - Determining the number of hidden units for an artificial neural network model
16. Bayesian learning for neural networks
17. Universal coding, information, prediction and estimation
18. Stochastic complexity and modeling
19. An optimal model selection of regression variables
20. Estimating the dimension of a model
21. Uniqueness of the weights for minimal feedforward nets with a given input-output map
22. Distribution of an information statistic and the criterion for the optimal model
23. On the essential difference between neural networks and regular statistical models
24. On the generalization error by a layered statistical model with Bayesian estimation
25. Algebraic analysis for singular statistical estimation
26. Algebraic analysis for nonregular learning machines
27. Algebraic analysis for nonidentifiable learning machines
28. Algebraic information geometry for learning machines with singularities
29. Probabilistic design of layered neural networks based on their unified framework
30. A decision-theoretic extension of stochastic complexity and its applications to learning