Lu decomposition and Toeplitz decomposition of a neural network

DOI10.1016/j.acha.2023.101601arXiv2211.13935MaRDI QIDQ6185692

Lek-Heng Lim, Yucong Liu, Simiao Jiao

Publication date: 30 January 2024

Published in: Applied and Computational Harmonic Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.13935

zbMATH Keywords

neural networksToeplitz matricesHankel matricesuniversal approximationtriangular matricesconvolutional neural networks

Mathematics Subject Classification ID

Factorization of matrices (15A23) Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Learning and adaptive systems in artificial intelligence (68T05) Approximation by other special function classes (41A30) Toeplitz, Cauchy, and related matrices (15B05)

Cites Work

• Unnamed Item
• Unnamed Item
• Every matrix is a product of Toeplitz matrices
• Products of three triangular matrices
• Multilayer feedforward networks are universal approximators
• Universality of deep convolutional neural networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Lu decomposition and Toeplitz decomposition of a neural network