Establishing criteria to ensure successful feedforward artificial neural network modelling of mechanical systems

DOI10.1016/S0895-7177(98)00018-1zbMath1185.74101OpenAlexW2009777990MaRDI QIDQ969828

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

Publication date: 8 May 2010

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

Full work available at URL: https://doi.org/10.1016/s0895-7177(98)00018-1

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Networks and the best approximation property
• Solution of nonlinear ordinary differential equations by feedforward neural networks
• Multilayer feedforward networks are universal approximators
• Optimal global rates of convergence for nonparametric regression
• A method of grid optimization for finite element methods
• Optimal \(h\)-\(p\) finite element methods
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Multivariate Smoothing Spline Functions
• Convergence Rates for Regularized Solutions
• Neural‐network‐based approximations for solving partial differential equations
• Ill-Conditioning in Neural Network Training Problems
• Approximation by superpositions of a sigmoidal function