Some implications of interval approach to dimension for network complexity

DOI10.1007/978-3-030-88817-6_13OpenAlexW4206369772MaRDI QIDQ2093971

Vera Kurková

Publication date: 27 October 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-88817-6_13

zbMATH Keywords

concentration of measurecovering numbershigh-dimensional geometryquasiorthogonal dimensionsparsity of feedforward networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05)

Cites Work

• Complexity estimates based on integral transforms induced by computational units
• Quasiorthogonal dimension of Euclidean spaces
• Weighted sums of certain dependent random variables
• Feedforward Neural Network Methodology
• Probability Inequalities for Sums of Bounded Random Variables
• A Measure of Asymptotic Efficiency for Tests of a Hypothesis Based on the sum of Observations
• Concentration of Measure for the Analysis of Randomized Algorithms
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Some implications of interval approach to dimension for network complexity