Information complexity of neural networks

Neural Networks

Volumn 13, Issue 3, 2000, Pages 365-375

  Kon, M A ^a   Plaskota, L ^b  

^a Boston University   (United States)

^b UNIVERSITY OF WARSAW   (Poland)

Author keywords

Complexity; Feedforward neural network; Information complexity; Learning; Neural complexity; Radial basis functions; RBF networks

Indexed keywords

COMPUTATIONAL COMPLEXITY; COMPUTER SYSTEMS PROGRAMMING; LEARNING SYSTEMS;

INFORMATION COMPLEXITY; RADIAL BASIS FUNCTION (RBF) NETWORKS;

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; INFORMATION; LEARNING; LINEAR SYSTEM; MATHEMATICS; NERVE CELL; PRIORITY JOURNAL;

AUTOMATIC DATA PROCESSING; MODELS, NEUROLOGICAL; NEURAL NETWORKS (COMPUTER);

EID: 0034065825     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(00)00015-0     Document Type: Article

References (18)

1. Aronszain N. Theory of reproducing kernels. Transactions of the American Mathematical Society. 68:1950;337-404.
2. Barron A.R. Universal approximation bounds for superposition of a sigmoidal function. IEEE Transactions in Information Theory. 39:1993;930-945.
3. Chui C.K., Li X., Mhaskar H.N. Neural networks for localized approximation. Center for Approximation Theory Report. 1993;289.
4. Chui C.K., Li X., Mhaskar H.N. Limitations of the approximation capabilities of neural networks with one hidden layer. Advances in Computational Mathematics. 5:1996;233-243.
5. Chui C.K., Li X. Approximation by ridge functions and neural networks with one hidden layer. Journal of Approximation Theory. 70:1992;131-141.
6. Girosi F., Poggio T. Networks and the best approximation property. Biological Cybernetics. 63:1990;169-176.
7. Melkman A.A., Micchelli C.A. Optimal estimation of linear operators in Hilbert spaces from inaccurate data. SIAM Journal on Numerical Analysis. 16:1979;87-105.
8. Mhaskar H.N. Neural networks and approximation theory. Neural Networks. 9:1996;721-722.
9. Mhaskar H.N., Micchelli C.A. Approximation by superposition of sigmoidal and radial basis functions. Advances in Applied Mathematics. 13:1992;350-373.
10. Mhaskar H.N., Micchelli C.A. Dimension independent bounds on the degree of approximation by neural networks. IBM Journal of Research and Development. 38:1994;277-284.
11. Mhaskar H.N., Micchelli C.A. Degree of approximation by neural and translation networks with a single hidden layer. Advances in Applied Mathematics. 161:1995;151-183.
12. Mhaskar H.N., Micchelli C.A. How to choose an activation function. Hanson S.J., Cowan J.D., Giles C.L. Advances in Neural Information Processing Systems. 5:1993;Morgan Kaufmann, San Mateo, CA.
13. Micchelli C.A., Buhmann M. On radial basis approximation on periodic grids. Mathematical Proceedings of the Cambridge Philosophical Society. 112:1992;317-334.
14. Pinkus A. n-Widths in approximation theory. 1985;Springer, Berlin.
15. Plaskota L. Noisy information and computational complexity. 1996;Cambridge University Press, Cambridge.
16. Poggio T., Girosi F. Regularization algorithms for learning that are equivalent to multilayer networks. Science. 247:1990;978-982.
17. Poggio, T., & Girosi, F. (1989). A theory of networks for approximation and learning, Artificial Intelligence Memoirs, 1140, MIT AI Lab.
18. Traub J.F., Wasilkowski G.W., Wozniakowski H. Information-based complexity. 1988;Academic Press, Boston, MA.