Weizmann Logo
ECCC
Electronic Colloquium on Computational Complexity

Under the auspices of the Computational Complexity Foundation (CCF)

Login | Register | Classic Style



REPORTS > DETAIL:

Paper:

TR94-024 | 12th December 1994 00:00

Polynomial Bounds for VC Dimension of Sigmoidal Neural Networks

RSS-Feed




TR94-024
Authors: Marek Karpinski, Angus Macintyre
Publication: 12th December 1994 00:00
Downloads: 3316
Keywords: 


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, the VC Dimension of analog neural
networks with the sigmoid activation function $\sigma(y)=1/1+e^{-y}$
to be bounded by a quadratic polynomial in the number of programmable
parameters.



ISSN 1433-8092 | Imprint