On the capabilities of higher-order neurons: a radial basis function approach
Michael Schmitt
Neural Computation 2004. ISSN 0899-7667

This is the latest version of this eprint.

Abstract

Higher-order neurons with $k$ monomials in $n$ variables are shown to have Vapnik-Chervonenkis (VC) dimension at least $nk+1$. This result supersedes the previously known lower bound obtained via $k$-term monotone disjunctive normal form (DNF) formulas. Moreover, it implies that the VC dimension of higher-order neurons with $k$ monomials is strictly larger than the VC dimension of $k$-term monotone DNF. The result is achieved by introducing an exponential approach that employs Gaussian radial basis function (RBF) neural networks for obtaining classifications of points in terms of higher-order neurons.

	PDF - Requires Adobe Acrobat Reader or other PDF viewer.
	Postscript - Requires a viewer, such as GhostView

Available Versions of this Item

• An improved VC dimension bound for sparse polynomials (deposited 18 May 2004)
  • On the capabilities of higher-order neurons: a radial basis function approach (deposited 23 November 2004) [Currently Displayed]

[Edit]