Deep learning via dynamical systems: an approximation perspective

DOI10.4171/jems/1221zbMath1528.41106arXiv1912.10382MaRDI QIDQ6172665

Qianxiao Li, Zuowei Shen, Ting Lin

Publication date: 20 July 2023

Published in: Journal of the European Mathematical Society (JEMS) (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.10382

zbMATH Keywords

controldynamical systemsapproximation theorydeep learningdeep neural networks

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Dynamical systems in control (37N35) Approximations and expansions (41A99)

Related Items (5)

Neural ODE Control for Classification, Approximation, and Transport ⋮ Dynamical Systems–Based Neural Networks ⋮ On mathematical modeling in image reconstruction and beyond ⋮ Deep Network Approximation for Smooth Functions ⋮ Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Relaxed variational problems
• Controllability questions for nonlinear systems in abstract spaces
• Affine systems in \(L_ 2(\mathbb{R}^d)\): The analysis of the analysis operator
• \(L^p\) approximation of maps by diffeomorphisms
• Controllability of nonlinear systems in Banach spaces: a survey
• Deep neural networks motivated by partial differential equations
• Variational networks: an optimal control approach to early stopping variational methods for image restoration
• Selection dynamics for deep neural networks
• Optimal approximation rate of ReLU networks in terms of width and depth
• Nonlinear approximation and (deep) ReLU networks
• Nonlinear approximation via compositions
• A priori estimates of the population risk for two-layer neural networks
• Error bounds for approximations with deep ReLU networks
• A mean-field optimal control formulation of deep learning
• A proposal on machine learning via dynamical systems
• The Embedding of Homeomorphisms in Flows
• Embedding diffeomorphisms in flows in Banach spaces
• Ten Lectures on Wavelets
• Vector fields generate few diffeomorphisms
• Deep distributed convolutional neural networks: Universality
• Stable architectures for deep neural networks
• EnResNet: ResNets Ensemble via the Feynman--Kac Formalism for Adversarial Defense and Beyond
• Error bounds for approximations with deep ReLU neural networks in Ws,p norms
• Deep Network Approximation for Smooth Functions
• Deep Network Approximation Characterized by Number of Neurons

This page was built for publication: Deep learning via dynamical systems: an approximation perspective