A regularity condition of the information matrix of a multilayer perceptron network

Neural Networks

Volumn 9, Issue 5, 1996, Pages 871-879

  Fukumizu, Kenji ^a  

^a RICOH COMPANY LTD   (Japan)

Author keywords

Information matrix; Irreducibility; Minimality; Multilayer perceptron; Parametric estimation; Sigmoidal function

Indexed keywords

GRAPH THEORY; INFORMATION THEORY; LEARNING SYSTEMS; OPTIMIZATION; PARAMETER ESTIMATION;

INFORMATION MATRIX; IRREDUCIBILITY; MINIMALITY; MULTILAYER PERCEPTRON NETWORK; SIGMOIDAL FUNCTION;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; PRIORITY JOURNAL;

EID: 0030198493     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(95)00119-0     Document Type: Article

References (15)

1. Ahlfors, L.V. (1966). Complex analysis (pp. 101-172). New York: McGraw-Hill.
2. Akaike H. A new look at the statistical model identification. IEEE Transactions on Automatic Control. 19(6):1974;716-723.
3. Amari, S. (1985). Differential-geometrical methods in statistics. Lecture notes in statistics 28. Berlin: Springer-Verlag.
4. Barron A.R. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory. 39:1993;930-945.
5. Chen A.M., Liu H., Hecht-Nielsen R. On the geometry of feedforward neural network error surfaces. Neural Computation. 5:1993;910-927.
6. Crameér, H. (1946). Mathematical method of statistics (pp.497-506). Princeton, NJ: Princeton University Press.
7. Cybenco G. Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals and Systems. 2(4):1989;303-314.
8. Funahashi K. On the approximate realization of continuous mapping by neural networks. Neural Networks. 2:1989;183-192.
9. Hagiwara, K., Toda, N., & Usui, S. (1993). On the problem of applying AIC to determine the structure of a layered feed-forward neural network. Proceedings of 1993 International Joint Conference on Neural Networks (pp.2263-2266).
10. Hornik K., Stinchcombe M., White H. Multi-layer feed-forward networks are universal approximators. Neural Networks. 2:1989;359-366.
11. Kȧrková V., Kainen P.C. Function equivalent feedforward neural networks. Neural Computation. 6:1994;543-558.
12. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning internal representations by error propagation. In D. E., Rumelhart, J. L. McClelland, & the PDP Research Group (eds.), Parallel distributed processing (Vol. 1, pp.318-362). Cambridge, MA: MIT Press.
13. Sussmann H.J. Uniqueness of the weights for minimal feed-forward nets with a given input-output map. Neural Networks. 5:1992;589-593.
14. Watanabe S., Fukumizu K. Probabilistic design of layered neural networks based on their unified framework. IEEE Transactions on Neural Networks. 6(3):1995;691-702.
15. White H. Learning in artificial neural networks: A statistical perspective. Neural Computation. 1:1989;425-464.