Approximation properties of local bases assembled from neural network transfer functions

DOI10.1016/S0895-7177(98)00144-7zbMath0999.93014OpenAlexW2009790961MaRDI QIDQ1596850

B. A. Zeldin, Andrew J. jun. Meade

Publication date: 5 May 2002

Published in: Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0895-7177(98)00144-7

zbMATH Keywords

neural networkstrainingfunction approximationshift-invariant subspaceslocal basis functions

Mathematics Subject Classification ID

Neural networks for/in biological studies, artificial life and related topics (92B20) System identification (93B30) Approximation by other special function classes (41A30)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Networks and the best approximation property
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Solution of nonlinear ordinary differential equations by feedforward neural networks
• Approximation by multiinteger translates of functions having global support
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Multivariate Smoothing Spline Functions
• Universal approximation bounds for superpositions of a sigmoidal function
• Approximation from Shift-Invariant Subspaces of L 2 (ℝ d )
• Ill-Conditioning in Neural Network Training Problems
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Approximation properties of local bases assembled from neural network transfer functions