Approximation of Functions by Perceptron Networks with Bounded Number of Hidden Units

 KURKOVA Vera
 Institute of Computer Science, Czech Academy of Sciences
Search this Article
Author(s)

 KURKOVA Vera
 Institute of Computer Science, Czech Academy of Sciences
Journal

 Neural Networks

Neural Networks 8(5), 745750, 19950701
References: 14

1
 Rate of approximation results motivated by robust neural network learning.

DARKEN C.
Proceedings of the 6th Annual ACM Conference on Computational Learning Theory, 303309, 1993
Cited by (3)

2
 Optimal nonlinear approximation

DEVORE R.
Manuscripia Mathematical 63, 469478, 1989
Cited by (1)

3
 Rates of convergence for radial basis functions and neural networks

GIROSI F.
Artificial Neural Networks for Speech and Vision, 97113, 1993
Cited by (2)

4
 Networks and the best approximation property

GIROSI F.
Biological Cybernetics 63, 169176, 1990
Cited by (12)

5
 <no title>

KURKOVA V.
Dimension independent rates of approximation by neural networks and variation with respect to halfspaces, 1995
Cited by (1)

6
 <no title>

SIMMONS F. G.
Introduction to Topology and Modern Analysis, 1963
Cited by (1)

7
 Approximating and learning unknown mappings using multilayer feedforward networks with bounded weights

STINCHCOMBE M.
Proceedings of IJCNN, III716, 1990
Cited by (1)

8
 Universal approximation bounds for superpositions of a sigmoidal function

BARRON A. R.
IEEE Trans. Inf. Theory 39(3), 930945, 1993
DOI Cited by (45)

9
 Approximation theory and feedforward networks.

BLUM E. K.
Neural Networks 4, 511515, 1991
Cited by (5)

10
 Some new results on neural network approximation

HORNIK K.
Neural Networks 6, 10691072, 1993
Cited by (12)

11
 Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

LESHNO M.
Neural Networks 6, 861867, 1993
DOI Cited by (23)

12
 Approximation by superposition of sigmoidal and radial basis functions

MHASKAR H. N.
Advances in Applied Mathematics 13, 350373, 1992
DOI Cited by (11)

13
 Dimension independent bounds on the degree of approximation by neural networks

MHASKAR H. N.
IBM Journal of Research and Development 38, 277284, 1994
Cited by (5)

14
 Universal approximation using radialbasisfunction networks

PARK J.
Neural Computation 3(2), 246257, 1991
DOI Cited by (27)
Cited by: 1

1
 Best approximation by Heaviside perceptron networks

KAINEN P. , KURKOVA V. , VOGT A.
Neural networks : the official journal of the International Neural Network Society 13(7), 695697, 20000901
References (14)