Volume 5, Number 1, 233-243, DOI: 10.1007/BF02124745

Limitations of the approximation capabilities of neural networks with one hidden layer

C. K. Chui, Xin Li and H. N. Mhaskar

View Related Documents

Abstract

LetsO( Î - s log(1/ Î ))\mathcal{O}( \in ^{ - s} log(1/ \in )) if a spline-like localization is required. This cannot be improved even if one allows different neurons to evaluate different activation functions, even depending upon the target function. Nevertheless, for anyO( Î - s - d )\mathcal{O}( \in ^{ - s - \delta } ) neurons can be constructed to provide this order of approximation, with localization. Analogous results are also valid for otherL p norms.

Keywords  Neural networks - Sobolev spaces - spline approximation - ridge functions

AMS subject classification  41A63 - 41A30 - 94C99

The research of this author was supported by NSF Grant # DMS 92-0698.
The research of this author was supported, in part, by AFOSR Grant #F49620-93-1-0150 and by NSF Grant #DMS 9404513.

Fulltext Preview

Image of the first page of the fulltext document