Universal approximation bounds for superpositions of a sigmoidal function
Universal approximation bounds for superpositions of a sigmoidal function
A. Barron
1993 · DOI: 10.1109/18.256500
IEEE Transactions on Information Theory · 3,430 Citations
TLDR
The approximation rate and the parsimony of the parameterization of the networks are shown to be advantageous in high-dimensional settings and the integrated squared approximation error cannot be made smaller than order 1/n/sup 2/d/ uniformly for functions satisfying the same smoothness assumption.