Scinovex
articleTop 10% cited

Layered Neural Networks with Gaussian Hidden Units as Universal Approximations

Neural Computation · 1990 · Vol. 2(2) · pp. 210–215
Eric HartmanJames D. KeelerJ. Kowalski

Abstract

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 .

Neural Networks and ApplicationsFuzzy Logic and Control SystemsImage Retrieval and Classification TechniquesArtificial neural networkGaussianRegular polygonMathematicsComputer scienceType (biology)AlgorithmArtificial intelligencePattern recognition (psychology)Applied mathematics
Citations
787
FWCI
14.53
field-weighted impact
References
13
Percentile
99%
vs. same field & year
Citations per year
Cited by
Fast Learning in Networks of Locally-Tuned Processing Units
Neural Computation · 1989 · 4,203 citations
Universal Approximation Using Radial-Basis-Function Networks
Neural Computation · 1991 · 4,027 citations
Neural networks and their applications
Review of Scientific Instruments · 1994 · 897 citations
Fuzzy systems as universal approximators
IEEE Transactions on Computers · 1994 · 939 citations
Neural Networks and the Bias/Variance Dilemma
Neural Computation · 1992 · 3,522 citations
References
Ergodic theory of chaos and strange attractors
Reviews of Modern Physics · 1985 · 4,848 citations
Multilayer feedforward networks are universal approximators
Neural Networks · 1989 · 20,841 citations
Fast Learning in Networks of Locally-Tuned Processing Units
Neural Computation · 1989 · 4,203 citations
Multilayer feedforward networks are universal approximators
Neural Networks · 1989 · 9,346 citations
Citation Network

How this paper connects to the literature. Drag to explore, click any node to open that paper.