Function approximation by deep neural networks with parameters \(\{0, \pm \frac{1}{2}, \pm 1,2\}\)

DOI10.1007/s42519-021-00229-5zbMath1478.62089arXiv2103.08659OpenAlexW3137945565MaRDI QIDQ2074650

Aleksandr Beknazaryan

Publication date: 10 February 2022

Published in: Journal of Statistical Theory and Practice (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.08659

zbMATH Keywords

entropyneural networksnonparametric regressionfunction approximation

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Nonparametric estimation (62G05) Artificial neural networks and deep learning (68T07) General theory of stochastic processes (60G07) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (1)

Nonparametric regression with modified ReLU networks

Cites Work

• Estimating a density under order restrictions: Nonasymptotic minimax risk
• A distribution-free theory of nonparametric regression
• Nonparametric regression using deep neural networks with ReLU activation function
• Error bounds for approximations with deep ReLU networks
• Convergence of stochastic processes
• Statistical guarantees for regularized neural networks

This page was built for publication: Function approximation by deep neural networks with parameters \(\{0, \pm \frac{1}{2}, \pm 1,2\}\)