On the Capabilities of Higher-Order Neurons: A Radial Basis Function Approach
From MaRDI portal
Recommendations
Cites work
- A general lower bound on the number of examples needed for learning
- Descartes' Rule of Signs for Radial Basis Function Neural Networks
- Localization vs. identification of semi-algebraic sets
- Neural Networks with Local Receptive Fields and Superlinear VC Dimension
- Neural networks with quadratic VC dimension
- New Designs for the Descartes Rule of Signs
- On the complexity of computing and learning with multiplicative neural networks
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
- VC Dimension and Uniform Learnability of Sparse Polynomials and Rational Functions
Cited in
(6)- Combined weight and density bounds on the polynomial threshold function representation of Boolean functions
- Sign-representation of Boolean functions using a small number of monomials
- scientific article; zbMATH DE number 1804095 (Why is no real title available?)
- An Upper Bound on the Minimum Number of Monomials Required to Separate Dichotomies of {−1, 1}n
- Learning Theory
- Minimal sign representation of Boolean functions: algorithms and exact results for low dimensions
This page was built for publication: On the Capabilities of Higher-Order Neurons: A Radial Basis Function Approach
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4673536)
