Neural networks with ReLU powers need less depth

DOI10.1016/J.NEUNET.2023.12.027MaRDI QIDQ6535869zbMATH OpenFDO

Authors Kurt Izak M. Cabanilla, Rhudaina Z. Mohammad, Jose Ernie C. Lope

Publication date 5 March 2024

Published in Neural Networks (Search for Journal in Brave)

zbMATH Keywords

approximation spacesdeep neural networksReLU powers

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Nonlinear approximation and (deep) ReLU networks
• Error bounds for approximations with deep ReLU networks
• Better approximations of high dimensional smooth functions by deep neural networks with rectified power units
• Deep vs. shallow networks: an approximation theory perspective
• SignReLU neural network and its approximation ability

Cites work

• scientific article; zbMATH DE number 477682 (Why is no real title available?)
• Approximation by superpositions of a sigmoidal function
• Approximation spaces of deep neural networks
• Deep learning
• Error bounds for approximations with deep ReLU networks
• Multilayer feedforward networks are universal approximators
• On the successive supersymmetric rank-1 decomposition of higher-order supersymmetric tensors
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations
• Tensor analysis. Spectral theory and special tensors

Cited in

(2)

• SignReLU neural network and its approximation ability
• Improving the expressive power of deep neural networks through integral activation transform

This page was built for publication: Neural networks with ReLU powers need less depth

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535869)