Tight bounds on rates of neural-network approximation

被引：0

作者：

Kurková, V

Sanguineti, M

机构：

[1] Acad Sci Czech Republ, Inst Comp Sci, Prague 18207 8, Czech Republic

[2] Univ Genoa, Dept Commun Comp & Syst Sci, I-16145 Genoa, Italy

来源：

ARTIFICIAL NEURAL NETWORKS-ICANN 2001, PROCEEDINGS | 2001年 / 2130卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Complexity of neural networks measured by the number of hidden units is studied in terms of rates of approximation. Limitations of improvements of upper bounds of the order of O(n(-1/2)) on such rates are investigated for perceptron networks with some periodic and sigmoidal activation functions.

引用

页码：277 / 282

页数：6

共 50 条

[1] Tightness of upper bounds on rates of neural-network approximation
Kurková, V
Sanguineti, M
ARTIFICIAL NEURAL NETS AND GENETIC ALGORITHMS, 2001, : 35 - 38
[2] Bounds on rates of variable-basis and neural-network approximation
Kurková, V
Sanguineti, M
IEEE TRANSACTIONS ON INFORMATION THEORY, 2001, 47 (06) : 2659 - 2665
[3] On Tractability of Neural-Network Approximation
Kainen, Paul C.
Kurkova, Vera
Sanguineti, Marcello
ADAPTIVE AND NATURAL COMPUTING ALGORITHMS, 2009, 5495 : 11 - +
[4] APPROXIMATION OF CHAOTIC BEHAVIOR BY USING NEURAL-NETWORK
NAGAYAMA, I
AKAMATSU, N
IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1994, E77D (04) : 450 - 458
[5] Neural-network approximation of functions of several variables
Alexeev D.V.
Journal of Mathematical Sciences, 2010, 168 (1) : 5 - 13
[6] SOME NEW RESULTS ON NEURAL-NETWORK APPROXIMATION
HORNIK, K
NEURAL NETWORKS, 1993, 6 (08) : 1069 - 1072
[7] Estimations of error bounds for neural-network function approximators
Townsend, NW
Tarassenko, L
IEEE TRANSACTIONS ON NEURAL NETWORKS, 1999, 10 (02): : 217 - 230
[8] On the optimality of neural-network approximation using incremental algorithms
Meir, R
Maiorov, VE
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2000, 11 (02): : 323 - 337
[9] TOWARD GENERATING NEURAL-NETWORK STRUCTURES FOR FUNCTION APPROXIMATION
NABHAN, TM
ZOMAYA, AY
NEURAL NETWORKS, 1994, 7 (01) : 89 - 99
[10] Bounds on the complexity of neural-network models and comparison with linear methods
Hlavácková-Schindler, K
Sanguineti, M
INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2003, 17 (02) : 179 - 194

← 1 2 3 4 5 →