A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces

DOI10.1002/MMA.5575zbMATH Open1416.41018OpenAlexW2924785619WikidataQ128195148 ScholiaQ128195148MaRDI QIDQ5223573FDOQ5223573

Liang Chen, Congwei Wu

Publication date: 18 July 2019

Published in: Mathematical Methods in the Applied Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1002/mma.5575

Recommendations

• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• Error bounds for approximations with deep ReLU networks
• Nonlinear approximation and (deep) ReLU networks
• New error bounds for deep ReLU networks using sparse grids
• Provable approximation properties for deep neural networks

zbMATH Keywords

curse of dimensionalityerror boundsbandlimited functionsdeep relu networks

Mathematics Subject Classification ID

Computational learning theory (68Q32) Rate of convergence, degree of approximation (41A25)

Cited In (10)

• A note on the applications of one primary function in deep neural networks
• Deep Network Approximation for Smooth Functions
• Deep ReLU Networks Overcome the Curse of Dimensionality for Generalized Bandlimited Functions
• Neural network approximation: three hidden layers are enough
• High-dimensional approximate r-nets
• On mathematical modeling in image reconstruction and beyond
• Optimal approximation rate of ReLU networks in terms of width and depth
• Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth
• Linearized two-layers neural networks in high dimension
• The construction and approximation of ReLU neural network operators

This page was built for publication: A note on the expressive power of deep rectified linear unit networks in high-dimensional spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5223573)