A constructive algorithm of neural approximation models for optimization problems

DOI10.1108/03321640910969520zbMATH Open1177.78063OpenAlexW2053293302MaRDI QIDQ3645129FDOQ3645129

Authors: Sara Carcangiu, Augusto Montisci, Alessandra Fanni 

Publication date: 16 November 2009

Published in: COMPEL: The International Journal for Computation and Mathematics in Electrical and Electronic Engineering (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1108/03321640910969520

Recommendations

• A fast algorithm for inversion of MLP networks in design problems
• The optimisation of electromagnetic devices using a combined finite element/neural network approach with on‐line training
• An evaluation of back-propagation neural networks for the optimal design of structural systems. II: Numerical evaluation
• An evaluation of back-propagation neural networks for the optimal design of structural systems. I: Training procedures
• Comparison of radial basis function approximation techniques

zbMATH Keywords

functional analysisneural netsoptimum designelectromagnetic devices

Mathematics Subject Classification ID

Programming involving graphs or networks (90C35) Optimization problems in optics and electromagnetic theory (78M50) Neural and heuristic methods applied to problems in optics and electromagnetic theory (78M32)

Cites Work

• Approximation by superpositions of a sigmoidal function
• Searching with iterated maps
• Title not available (Why is that?)
• An efficient hybrid algorithm for the optimization of problems with several local minima

Cited In (9)

• Performance of a coordinate search ANN training algorithm
• A neural model for the \(p\)-median problem
• Handling of the radiative electron emission modeling results by use of the neural networks
• Multi‐directional search to optimize neural network error function
• Neural computation for robust approximate pole assignment
• Optimizing multilayer perceptrons to approximate nonlinear quaternion functions
• Optimal design method to automobile problems using holographic neural network's approximation
• Performance of derivative free search ANN training algorithm with time series and classification problems
• A fast algorithm for inversion of MLP networks in design problems

This page was built for publication: A constructive algorithm of neural approximation models for optimization problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3645129)