Author： Karpinski M. Macintyre A.
Publisher： Academic Press
ISSN： 0022-0000
Source： Journal of Computer and System Sciences, Vol.54, Iss.1, 1997-02, pp. : 169-176
Disclaimer: Any content in publications that violate the sovereignty, the constitution or regulations of the PRC is not accepted or approved by CNPIEC.
Abstract
We introduce a new method for proving explicit upper bounds on the VC dimension of general functional basis networks and prove as an application, for the first time, that the VC dimension of analog neural networks with the sigmoidal activation function sigma ( y )=1/1+ e - y is bounded by a quadratic polynomial O (( lm ) 2 ) in both the number l of programmable parameters, and the number m of nodes. The proof method of this paper generalizes to much wider class of Pfaffian activation functions and formulas and gives also for the first time polynomial bounds on their VC dimension. We present also some other applications of our method.
Related content
Neural Networks with Quadratic VC Dimension
Journal of Computer and System Sciences, Vol. 54, Iss. 1, 1997-02 ,pp. :
Access to resources
Recommend
Approximation and Estimation Bounds for Artificial Neural Networks
By Barron A.R.
Machine Learning, Vol. 14, Iss. 1, 1994-01 ,pp. :