On the Capabilities of Higher-Order Neurons: A Radial Basis Function Approach
From MaRDI portal
Publication:4673536
DOI10.1162/0899766053019953zbMath1059.92013OpenAlexW2156362238WikidataQ62492572 ScholiaQ62492572MaRDI QIDQ4673536
Publication date: 29 April 2005
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/0899766053019953
Related Items (4)
Sign-representation of Boolean functions using a small number of monomials ⋮ Combined weight and density bounds on the polynomial threshold function representation of Boolean functions ⋮ Minimal Sign Representation of Boolean Functions: Algorithms and Exact Results for Low Dimensions ⋮ An Upper Bound on the Minimum Number of Monomials Required to Separate Dichotomies of {−1, 1}n
Cites Work
- Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
- Neural networks with quadratic VC dimension
- Localization vs. identification of semi-algebraic sets
- A general lower bound on the number of examples needed for learning
- On the Complexity of Computing and Learning with Multiplicative Neural Networks
- VC Dimension and Uniform Learnability of Sparse Polynomials and Rational Functions
- Neural Networks with Local Receptive Fields and Superlinear VC Dimension
- New Designs for the Descartes Rule of Signs
- Descartes' Rule of Signs for Radial Basis Function Neural Networks
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
This page was built for publication: On the Capabilities of Higher-Order Neurons: A Radial Basis Function Approach
