A tight upper bound on the generalization error of feedforward neural networks

DOI10.1016/j.neunet.2020.04.001zbMath1468.68167OpenAlexW3015482436WikidataQ91866110 ScholiaQ91866110MaRDI QIDQ1982395

Aydin Sarraf

Publication date: 8 September 2021

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2020.04.001

zbMATH Keywords

feedforward neural networksgeneralization error

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Robustness and generalization
• Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
• Three fundamental concepts of the capacity of learning machines
• Bounding the Vapnik-Chervonenkis dimension of concept classes parameterized by real numbers
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Local Rademacher complexities
• Distribution-free performance bounds for potential function rules
• Neural Nets with Superlinear VC-Dimension
• Scale-sensitive dimensions, uniform convergence, and learnability
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Robust Large Margin Deep Neural Networks
• 10.1162/153244302760200704
• 10.1162/153244303321897690
• Estimation of Dependences Based on Empirical Data

This page was built for publication: A tight upper bound on the generalization error of feedforward neural networks