An analysis of training and generalization errors in shallow and deep networks

DOI10.1016/j.neunet.2019.08.028zbMath1434.68513arXiv1802.06266OpenAlexW2972277540WikidataQ90416114 ScholiaQ90416114MaRDI QIDQ2185668

Tomaso Poggio, Hrushikesh N. Mhaskar

Publication date: 5 June 2020

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

Full work available at URL: https://arxiv.org/abs/1802.06266

zbMATH Keywords

generalization errordeep learninginterpolatory approximation

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Related Items (2)

Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018 ⋮ A direct approach for function approximation on data defined manifolds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Minimum Sobolev norm interpolation with trigonometric polynomials on the torus
• Sur l'approximation d'une fonction périodique et de ses dérivées successives par un polynôme trigonométrique et par ses dérivées successives
• Eignets for function approximation on manifolds
• Function approximation with zonal function networks with activation functions analogous to the rectified linear unit functions
• Degree of approximation by neural and translation networks with a single hidden layer
• On some convergence properties of the interpolation polynomials
• Deep vs. shallow networks: An approximation theory perspective
• Robust Large Margin Deep Neural Networks
• Localized Linear Polynomial Operators and Quadrature Formulas on the Sphere
• Applications of classical approximation theory to periodic basis function networks and computational harmonic analysis
• Approximation with interpolatory constraints

This page was built for publication: An analysis of training and generalization errors in shallow and deep networks