Gabor neural networks with proven approximation properties

DOI10.1007/s12220-020-00575-zOpenAlexW3119949288WikidataQ114221041 ScholiaQ114221041MaRDI QIDQ2050710

Wojciech Czaja, Yiran Li

Publication date: 31 August 2021

Published in: The Journal of Geometric Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s12220-020-00575-z

zbMATH Keywords

approximation theoryGabor framedeep neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Trigonometric approximation (42A10) General harmonic expansions, frames (42C15)

Cites Work

• Unnamed Item
• Continuity properties of the Gabor frame operator
• A unified characterization of reproducing systems generated by a finite family. II
• Oversampling, quasi-affine frames, and wave packets
• Foundations of time-frequency analysis
• A unified characterization of reproducing systems generated by a finite family
• Provable approximation properties for deep neural networks
• Discrete directional Gabor frames
• Rotationally invariant time-frequency scattering transforms
• Regularity of dual Gabor windows
• Analysis of time-frequency scattering transforms
• Group Invariant Scattering
• Continuous and Discrete Reproducing Systems That Arise from Translations. Theory and Applications of Composite Wavelets
• Wilson Bases and Modulation Spaces
• Universal approximation bounds for superpositions of a sigmoidal function
• A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction
• Lipschitz properties for deep convolutional networks
• Deep Neural Network Approximation Theory
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• A Class of Nonharmonic Fourier Series
• Approximation by superpositions of a sigmoidal function
• Weyl-Heisenberg frames, translation invariant systems and the Walnut representation

This page was built for publication: Gabor neural networks with proven approximation properties