Mathematics – Optimization and Control
Scientific paper
2001-12-19
Mathematics
Optimization and Control
9 pages, submitted for publication. Various typos fixed and the proof of the main result has been streamlined
Scientific paper
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.
Rojas Maurice J.
Vidyasagar Mathukumalli
No associations
LandOfFree
An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-314842