Butterfly-Net: Optimal Function Representation Based on Convolutional Neural Networks
From MaRDI portal
Publication:5162362
DOI10.4208/cicp.OA-2020-0214OpenAlexW3100023701MaRDI QIDQ5162362
Xiuyuan Cheng, Yingzhou Li, Jian-feng Lu
Publication date: 2 November 2021
Published in: Communications in Computational Physics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1805.07451
Artificial neural networks and deep learning (68T07) Factorization of matrices (15A23) Iterative numerical methods for linear systems (65F10) Numerical interpolation (65D05) Rate of convergence, degree of approximation (41A25)
Related Items
Growth Factors of Random Butterfly Matrices and the Stability of Avoiding Pivoting ⋮ Error bounds for approximations using multichannel deep convolutional neural networks with downsampling ⋮ A Multiscale Neural Network Based on Hierarchical Matrices ⋮ A multiscale neural network based on hierarchical nested bases
Uses Software
Cites Work
- Unnamed Item
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Multilayer feedforward networks are universal approximators
- Multidimensional butterfly factorization
- BCR-net: A neural network based on the nonstandard wavelet form
- An algorithm for the rapid evaluation of special function transforms
- Error bounds for approximations with deep ReLU networks
- Universality of deep convolutional neural networks
- MgNet: a unified framework of multigrid and convolutional neural network
- Solving for high-dimensional committor functions using artificial neural networks
- A multiscale neural network based on hierarchical nested bases
- Deep vs. shallow networks: An approximation theory perspective
- A Stable and Accurate Butterfly Sparse Fourier Transform
- A Butterfly Algorithm for Synthetic Aperture Radar Imaging
- Discrete Symbol Calculus
- Representational Power of Restricted Boltzmann Machines and Deep Belief Networks
- Fast Computation of Fourier Integral Operators
- Sparse Fourier Transform via Butterfly Algorithm
- A Fast Butterfly Algorithm for the Computation of Fourier Integral Operators
- Universal approximation bounds for superpositions of a sigmoidal function
- Optimal Approximation with Sparsely Connected Deep Neural Networks
- Butterfly Factorization
- Image restoration: Total variation, wavelet frames, and beyond
- Image Processing and Analysis
- Interpolative Butterfly Factorization
- Approximation by superpositions of a sigmoidal function
