Layered Neural Networks with Gaussian Hidden Units as Universal Approximations

被引：521

作者：

Hartman, Eric J. ^{[1
]}

Keeler, James D. ^{[1
]}

Kowalski, Jacek M. ^{[2
]}

机构：

[1] Microelect & Comp Technol Corp MCC, 3500 West Balcones Ctr Dr, Austin, TX 78759 USA

[2] Univ North Texas, Dept Phys, Denton, TX 76203 USA

来源：

NEURAL COMPUTATION | 1990年 / 2卷 / 02期

关键词：

D O I：

10.1162/neco.1990.2.2.210

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

A neural network with a single layer of hidden units of gaussian type is proved to be a universal approximator for real-valued maps defined on convex, compact sets of R-n.

引用

页码：210 / 215

页数：6

共 15 条

[1] Product Units: A Computationally Powerful and Biologically Plausible Extension to Backpropagation Networks [J].

Durbin, Richard ;

Rumelhart, David E. .

NEURAL COMPUTATION, 1989, 1 (01) :133-142

[2] ERGODIC-THEORY OF CHAOS AND STRANGE ATTRACTORS [J].

ECKMANN, JP ;

RUELLE, D .

REVIEWS OF MODERN PHYSICS, 1985, 57 (03) :617-656

[3] ON THE APPROXIMATE REALIZATION OF CONTINUOUS-MAPPINGS BY NEURAL NETWORKS [J].

FUNAHASHI, K .

NEURAL NETWORKS, 1989, 2 (03) :183-192

[4]

Hornik M., 1989, NEURAL NETW IN PRESS

[5]

Lapedes A., 1987, LAUR88418 LOS AL NAT

[6]

Lee S., 1988, IEEE INT C NEUR NETW, P1

[7]

Lorentz G. G., 1986, APPROXIMATIONS FUNCT

[8]

MEDGYESSY P, 1961, DECOMPOSITION SUPERP

[9]

Moody J., 1989, PREPRINT

[10]

MOODY J, 1989, P 1988 CONN MOD SUMM

← 1 2 →