New study on neural networks: the essential order of approximation

Authors:
Jianjun Wang;Zongben Xu
Affiliations:
School of Mathematics & Statistics, Southwest University, Chongqing, 400715, PR China and Institute for Information and System Science, Xi'an Jiaotong University, Xi'an, Shaan'xi, 710049, PR China;Institute for Information and System Science, Xi'an Jiaotong University, Xi'an, Shaan'xi, 710049, PR China
Venue:
Neural Networks
Year:
2010

Citing 17
Cited 1

Multilayer feedforward networks are universal approximators

Neural Networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks

Neural Networks
Approximation of functions on a compact set by finite sums of a sigmoid function without scaling

Neural Networks
Original Contribution: Approximation of a function and its derivative with a neural network

Neural Networks
Approximation by superposition of sigmoidal and radial basis functions

Advances in Applied Mathematics
Approximation by ridge functions and neural networks with one hidden layer

Journal of Approximation Theory
Original Contribution: Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Neural Networks
Dimension-independent bounds on the degree of approximation by neural networks

IBM Journal of Research and Development
Regular Article: Degree of Approximation by Neural and Translation Networks with a Single Hidden Layer

Advances in Applied Mathematics
Estimates of the number of hidden units and variation with respect to half-spaces

Neural Networks
Approximation of functions by a multilayer perceptron: a new approach

Neural Networks
Constructive function-approximation by three-layer artificial neural networks

Neural Networks
Neural networks for optimal approximation of smooth and analytic functions

Neural Computation
Efficient estimation of neural weights by polynomial approximation

IEEE Transactions on Information Theory
Universal approximation bounds for superpositions of a sigmoidal function

IEEE Transactions on Information Theory
Approximation bounds for smooth functions in C(Rd) by neural and mixture networks

IEEE Transactions on Neural Networks

Synchronization Criteria for an Array of Neutral-Type Neural Networks with Hybrid Coupling: A Novel Analysis Approach

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

For the nearly exponential type of feedforward neural networks (neFNNs), the essential order of their approximation is revealed. It is proven that for any continuous function defined on a compact set of R^d, there exist three layers of neFNNs with the fixed number of hidden neurons that attain the essential order. Under certain assumption on the neFNNs, the ideal upper bound and lower bound estimations on approximation precision of the neFNNs are provided. The obtained results not only characterize the intrinsic property of approximation of the neFNNs, but also proclaim the implicit relationship between the precision (speed) and the number of hidden neurons of the neFNNs.