Existence and uniqueness results for neural network approximations

Authors:
R. C. Williamson;U. Helmke
Affiliations:
Dept. of Syst. Eng., Australian Nat. Univ., Canberra, ACT;-
Venue:
IEEE Transactions on Neural Networks
Year:
1995

Citing 0
Cited 4

On the partitioning capabilities of feedforward neural networks with sigmoid nodes

Neural Computation
Computational Properties of Networks of Synchronous Groups of Spiking Neurons

Neural Computation
Application of radial basis function and generalized regression neural networks in non-linear utility function specification for travel mode choice modelling

Mathematical and Computer Modelling: An International Journal
Establishing criteria to ensure successful feedforward artificial neural network modelling of mechanical systems

Mathematical and Computer Modelling: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Some approximation theoretic questions concerning a certain class of neural networks are considered. The networks considered are single input, single output, single hidden layer, feedforward neural networks with continuous sigmoidal activation functions, no input weights but with hidden layer thresholds and output layer weights. Specifically, questions of existence and uniqueness of best approximations on a closed interval of the real line under mean-square and uniform approximation error measures are studied. A by-product of this study is a reparametrization of the class of networks considered in terms of rational functions of a single variable. This rational reparametrization is used to apply the theory of Pade approximation to the class of networks considered. In addition, a question related to the number of local minima arising in gradient algorithms for learning is examined