Computer validation of neural network dynamics: a first case study

DOI10.3934/DCDSB.2024145MaRDI QIDQ7012043zbMATH OpenFDO

Authors Christian Kuehn, Elena Queirolo

Publication date 18 March 2025

Published in Discrete and Continuous Dynamical Systems. Series B (Search for Journal in Brave)

Full work available at URL https://doi.org/10.3934/DCDSB.2024145

zbMATH Keywords

dimension theorydiscrete-time modelmultifractal analysisPoincaré recurrencessingular Hopf bifurcation

Mathematics Subject Classification ID

Computational methods for bifurcation problems in dynamical systems (37M20) Artificial neural networks and deep learning (68T07)

Cites work

• A mean field view of the landscape of two-layer neural networks
• A proof of Wright's conjecture
• A proposal on machine learning via dynamical systems
• Automatic differentiation for Fourier series and the radii polynomial approach
• CAPD::DynSys: a flexible C++ toolbox for rigorous numerical analysis of dynamical systems
• Centennial History of Hilbert's 16th Problem
• Computer-assisted methods for the study of stationary solutions in dissipative systems, applied to the Kuramoto-Sivashinski equation
• Computing (un)stable manifolds with validated error bounds: non-resonant and resonant spectra
• Elements of applied bifurcation theory
• Global bifurcation diagrams of steady states of systems of PDEs via rigorous numerics: a 3-component reaction-diffusion system
• scientific article; zbMATH DE number 2152346 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• scientific article; zbMATH DE number 1440908 (Why is no real title available?)
• Machine learning: Trends, perspectives, and prospects
• Machine learning. A probabilistic perspective
• MATCONT
• Multiple time scale dynamics
• Multiscale analysis of slow-fast neuronal learning models with noise
• Nonlinear oscillations, dynamical systems, and bifurcations of vector fields
• Parameterization method for unstable manifolds of delay differential equations
• Rigorous numerics for analytic solutions of differential equations: the radii polynomial approach
• Rigorous validation of a Hopf bifurcation in the Kuramoto-Sivashinsky PDE
• Rigorous verification of Hopf bifurcations via desingularization and continuation
• The Lorenz attractor exists
• Turnpike in optimal control of PDEs, ResNets, and beyond
• Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks
• Validated Continuation for Equilibria of PDEs

This page was built for publication: Computer validation of neural network dynamics: a first case study

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q7012043)