An Improved Bound on the VC-Dimension of Neural Networks with Polynomial Activation Functions
J. Maurice Rojas, M. Vidyasagar
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.
Create a lesson
Related papers
Compositional Sensitivity Analysis for Multiobjective System Co-Design
Alan Bonomi, Antonio Terpin, Yubo Cai et al.
Optimal Decay Matrix Control Barrier Functions: Soundness and Completeness for Matrix Safety Constraints
Samuel G. Gessow, Albert Wu, Aaron D. Ames et al.
Dynamic Programming for A Linear-Gaussian Dual Control Problem
Ying Wang, Yuchao Li, Håkan Hjalmarsson
Local-discrepancy ambiguity sets for distributionally robust optimization
Ilias Papagoudis, Dimitris Boskos
Hamiltonian Primal-Dual Policy Reinforcement Learning for Derivative-Free Model-Based Control
K. Rabiei, Z. Rui, X. Lu et al.
Connection between MP and DPP for Mean-Field Stochastic Optimal Control Problems
Guangzhi Cui, Tianyang Nie, Guangchen Wang