Mean-field limits of trained weights in deep learning: a dynamical systems perspective

DOI10.14658/PUPJ-DRNA-2022-3-12zbMATH Open1540.68229MaRDI QIDQ6556653

Alexandre Smirnov, Houman Owhadi, B. Hamzi

Publication date: 17 June 2024

Published in: Dolomites Research Notes on Approximation (Search for Journal in Brave)

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Approximation by other special function classes (41A30) Approximation methods and numerical treatment of dynamical systems (37M99)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Kernel methods in machine learning
• Hedonic housing prices and the demand for clean air
• Multisymplectic geometry, variational integrators, and nonlinear PDEs
• Operator-valued kernels for learning from functional response data
• Discrete mechanics and variational integrators
• Support Vector Machines

Related Items (1)

5-th Dolomites Workshop on Constructive Approximation and Applications -- special issue dedicated to Robert Schaback on the occasion of his 75th birthday

This page was built for publication: Mean-field limits of trained weights in deep learning: a dynamical systems perspective

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6556653)