[ACM Press the twenty-seventh annual ACM
โ
Karpinski, Marek; Macintyre, Angus
๐
Article
๐
1995
๐
ACM Press
๐
English
โ 647 KB
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 polynom