Minimization of error functionals over perceptron networks

Neural Computation

Volumn 20, Issue 1, 2008, Pages 252-270

  Kůrková, Věra ^a  

^a INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; BIOLOGICAL RHYTHM; COMPUTER SIMULATION; LOGIC; NORMAL DISTRIBUTION; PHYSIOLOGY;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; BIOLOGICAL CLOCKS; COMPUTER SIMULATION; LOGIC; NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION;

EID: 37748999976     PISSN: 08997667     EISSN: 1530888X     Source Type: Journal    
DOI: 10.1162/neco.2008.20.1.252     Document Type: Article

References (35)

1. Adams, R. A., & Fournier, J. J. F. (2003). Sobolev spaces. Orlando, FL: Academic Press.
2. Barron, A. R. (1992). Neural net approximation. In K. Narenda (Ed.), Proceedings of the 7th Yale Workshop on Adaptive and Learning Systems (pp. 69-72). New Haven, CT: Yale University Press.
3. Barron, A. R. (1993). Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans. on Information Theory, 39, 930-945.
4. Cheang, G. H. L., & Barron, A. R. (2000). A better approximation for balls. Journal of Approximation Theory, 104, 183-203.
5. Cucker, F., & Smale, S. (2002). On the mathematical foundations of learning. Bulletin of AMS, 39, 1-49.
6. Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control and Signals Systems, 2, 303-314.
7. Fine, T. L. (1999). Feedforward neural networks methodology. New York: Springer-Verlag.
8. Hornik, K., Stinchcombe, M., & White, H. (1989). Multi-layer feedforward networks are universal approximators. Neural Networks, 2, 359-366.
9. Ito, Y. (1991). Representation of functions by superpositions of a step or sigmoid function and their applications to neural network theory. Neural Networks, 4, 385-394.
10. Ito, Y. (1992). Finite mapping by neural networks and truth functions. Math. Scientist, 17, 69-77.
11. Jones, L. K. (1992). A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annals of Statistics, 20, 608-613.
12. Kainen, P. C., & Kůrková, V. (1993). Quasiorthogonal dimension of Euclidean spaces. Applied Math. Letters, 6, 7-10.
13. Kainen, P. C., Kůrková, V., & Vogt, A. (1999). Approximation by neural networks is not continuous. Neurocomputing, 29, 47-56.
14. Kainen, P. C., Kůrková, V., & Vogt, A. (2000a). Geometry and topology of continuous best and near best approximations. Journal of Approximation Theory, 105, 252-262.
15. Kainen, P. C., Kůrková, V., & Vogt, A. (2000b). An integral formula for Heaviside neural networks. Neural Network World, 10, 313-320.
16. Kainen, P. C., Kůrková, V., & Vogt, A. (2003). Best approximation by linear combinations of characteristic functions of half-spaces. Journal of Approximation Theory, 122, 151-159.
17. Kainen, P. C., Kůrková, V., & Vogt, A. (2006). Integral combinations of Heavisides. Submitted, Research report ICS-966. Available online at http://www.es.cas.cz/research/publications.shtml.
18. Kainen, P. C., Kůrková, V., & Vogt, A. (2007). A Sobolev-type upper bound for rates of approximation by linear combinations of plane waves. Journal of Approximation Theory, 147, 1-10.
19. Kůrková, V. (1997). Dimension-independent rates of approximation by neural networks. In K. Warwick & M. Kárný (Eds.), Computer-intensive methods in control and signal processing: The curse of dimensionality (pp. 261-270). Boston: Birkhauser.
20. Kůrková, V. (2003). High-dimensional approximation and optimization by neural networks. In J. Suykens, G. Horvath, S. Basu, C. Micchelli, & J. Vandewalle (Eds.), Advances in learning theory: Methods, models and applications (pp. 69-88). Amsterdam: IOS Press.
21. Kůrková, V. (2005). Minimization of empirical error functional over perceptron networks. In B. Ribeiro, R. F. Albrecht, A. Dobnikar, D. W. Pearson, & N. C. Steele (Eds.), Adaptive and natural computing algorithms (pp. 46-49). Berlin: Springer-Verlag.
22. Kůrková, V., Kainen, P. C., & Kreinovich, V. (1997). Estimates of the number of hidden units and variation with respect to half-spaces. Neural Networks, 10, 1061-1068.
23. Kůrková, V., Savický, P., & Hlaváč ková, K. (1998). Representations and rates of approximation of real-valued Boolean functions by neural networks. Neural Networks, 11, 651-659.
24. Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993). Multilayer feedforward networks with a non-polynomial activation can approximate any function. Neural Networks, 6, 861-867.
25. Makovoz, Y. (1996). Random approximants and neural networks. Journal of Approximation Theory, 85, 98-109.
26. Makovoz, Y. (1998). Uniform approximation by neural networks. Journal of Approximation Theory, 95, 215-228.
27. Mhaskar, H. N., & Micchelli, C. A. (1992). Approximation by superposition of a sigmoidal function. Advances in Applied Mathematics, 13, 350-373.
28. Pinkus, A. (1998). Approximation theory of the MPL model in neural networks. Acta Numerica, 8, 277-283.
29. Pisier, G. (1981). Remarques sur un résultat non publié de B. Maurey. In Séminaire d'Analyse Fonctionnelle 1980-81. Palaiseau, France: Ecole Polytechnique, Centre de Mathématiques.
30. Savický, P. (1994). On the bent Boolean functions that are symmetric. European Journal of Combinatorics, 15, 145-168.
31. Shläfli, L. (1950). Gesamelte mathematische abhandlungen. Basel: Birkhäuzer.
32. Singer, I. (1970). Best approximation in normed linear spaces by elements of linear subspaces. Berlin: Springer-Verlag.
33. Strichartz, R. S. (2003). A guide to distribution theory and Fourier transforms. Singapore: World Scientific.
34. Vapnik, V. N. (1995). The nature of statistical learning theory. New York: Springer-Verlag.
35. Werbos, P. J. (1985). Backpropagation: Basics and new developments. In M. Arbib (Ed.), The handbook of brain theory and neural networks (pp. 134-139). Cambridge, MA: MIT Press.