Universal approximation with quadratic deep networks

DOI10.1016/j.neunet.2020.01.007zbMath1434.68506arXiv1808.00098OpenAlexW2999571325WikidataQ89730519 ScholiaQ89730519MaRDI QIDQ2185719

Ge Wang, Jinjun Xiong, Feng-lei Fan

Publication date: 5 June 2020

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

Full work available at URL: https://arxiv.org/abs/1808.00098

zbMATH Keywords

approximation theorydeep learningquadratic networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15)

Related Items (3)

Feasibility-based fixed point networks ⋮ Quadratic Neural Networks for Solving Inverse Problems ⋮ Shaping Dynamics With Multiple Populations in Low-Rank Recurrent Networks

Uses Software

• ImageNet
• AlexNet

Cites Work

• Unnamed Item
• Unnamed Item
• Approximation theory in tensor product spaces
• Why does deep and cheap learning work so well?
• Multilayer feedforward networks are universal approximators
• Probabilistic lower bounds for approximation by shallow perceptron networks
• Deep vs. shallow networks: An approximation theory perspective
• Universal approximation bounds for superpositions of a sigmoidal function
• Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems
• Dependence of Computational Models on Input Dimension: Tractability of Approximation and Optimization Tasks

This page was built for publication: Universal approximation with quadratic deep networks