paper

An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions

arXiv:math/0112208

Abstract

In this note, we derive an improved upper bound for the VC-dimension of neural networks with polynomial activation functions. This improved bound is based on a result of Rojas on the number of connected components of a semi-algebraic set.

9 pages, submitted for publication. Various typos fixed and the proof of the main result has been streamlined