An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions Institutional Repository Document uri icon

abstract

  • 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.

author list (cited authors)

  • Rojas, J. M., & Vidyasagar, M.

complete list of authors

  • Rojas, J Maurice||Vidyasagar, M

Book Title

  • arXiv

publication date

  • December 2001