Training neural networks with noisy data as an ill-posed problem

DOI10.1023/A:1016641629556zbMath1126.41301OpenAlexW1723924088MaRDI QIDQ5934295

Heinz W. Engl, Martin Burger

Publication date: 19 June 2001

Published in: Advances in Computational Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1016641629556

zbMATH Keywords

neural networksill-posed problemsleast square collocation

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) Spline approximation (41A15) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Approximation by other special function classes (41A30) Theoretical approximation of solutions to integral equations (45L05)

Related Items (10)

Two-Layer Neural Networks with Values in a Banach Space ⋮ Discretization of parameter identification in PDEs using neural networks ⋮ On spectral windows in supervised learning from data ⋮ Variational regularization in inverse problems and machine learning ⋮ Data driven regularization by projection ⋮ Multiscale support vector approach for solving ill-posed problems ⋮ Regularized greedy algorithms for network training with data noise ⋮ The weight-decay technique in learning from data: an optimization point of view ⋮ Error bounds for approximation with neural networks ⋮ Best \(k\)-layer neural network approximations

This page was built for publication: Training neural networks with noisy data as an ill-posed problem