Publication View

An Improved Bound on the VC-Dimension of (2007)

Abstract
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 [Roj00] on the number of connected components of a semi-algebraic set.

Publication details
Download http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.7.7981
Source http://www.math.tamu.edu/~rojas/sagarrojas.ps.gz
Contributors CiteSeerX
Repository CiteSeerX - Scientific Literature Digital Library and Search Engine (United States)
Type text
Language English
Relation 10.1.1.66.1613, 10.1.1.35.5527, 10.1.1.23.5457