Institut für Informatik   Abteilung V

 Universität Bonn -> Institut für Informatik -> Abteilung V CS-Reports 1994 Copyright 1994 Universität Bonn, Institut für Informatik, Abt. V 85116 Polynomial Bounds for VC Dimension of Sigmoidal Neural Networks Marek Karpinski, Angus Macintyre [Download PostScript] [Download PDF] 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. Last Change: 11/05/14 at 09:51:10  English Universität Bonn -> Institut für Informatik -> Abteilung V