Approximation capabilities of measure-preserving neural networks

DOI10.1016/j.neunet.2021.12.007arXiv2106.10911OpenAlexW3174926092MaRDI QIDQ6072433

Aiqing Zhu, Pengzhan Jin, Yi-Fa Tang

Publication date: 13 October 2023

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2106.10911

zbMATH Keywords

dynamical systemsneural networksapproximation theorymeasure-preserving

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Dynamical systems and ergodic theory (37-XX) Approximations and expansions (41-XX)

Cites Work

• Unnamed Item
• \(L^p\) approximation of maps by diffeomorphisms
• Volume-preserving algorithms for source-free dynamical systems
• Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness
• Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems
• A mean-field optimal control formulation of deep learning
• A proposal on machine learning via dynamical systems
• Solving Ordinary Differential Equations I
• Large-Scale Machine Learning with Stochastic Gradient Descent
• Polar factorization and monotone rearrangement of vector‐valued functions
• Polynomial approximations of symplectic dynamics and richness of chaos in non-hyperbolic area-preserving maps
• DeepXDE: A Deep Learning Library for Solving Differential Equations
• Geometric Numerical Integration
• Approximation by superpositions of a sigmoidal function
• Neural network approximation: three hidden layers are enough

This page was built for publication: Approximation capabilities of measure-preserving neural networks