Polynomial bounds for VC dimension of sigmoidal neural networks
Marek Karpiński, Angus J. Macintyre · 1995
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 o(y) = 1/1 + e-y to be bounded by a quadratic polynomial in the number of programmable parameters.O