An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions

J. Maurice Rojas, Mathukumalli Vidyasagar · arXiv (Cornell University) · 2001

In this note, we derive an improved upper bound for the VC-dimension of neural networks with polynomial activation functions. This improved bound is based on a result of Rojas on the number of connected components of a semi-algebraic set.

Read the paper · More papers on PaperTik