Uniform approximation and the complexity of neural networks
Paulo J. S. G. Ferreira, Si-Qi Cao · 2002
Studies some of the approximating properties of feedforward neural networks as a function of the number of nodes. Two cases are considered: sigmoidal and radial basis function networks. Bounds for the approximation error are given. The methods through which we arrive at the bounds are constructive. The error studied is the L/sub /spl infin// or sup error.