Orthogonal considerations in the design of neural networks for function approximation.

DOI10.1016/0378-4754(95)00062-3zbMATH Open1080.68620OpenAlexW1981041801MaRDI QIDQ816796FDOQ816796

Authors: N. E. Zubov 

Publication date: 24 February 2006

Published in: Mathematics and Computers in Simulation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0378-4754(95)00062-3

Recommendations

• Properties and performance of orthogonal neural network in function approximation
• Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation
• On function recovery by neural networks based on orthogonal expansions
• Number determination of hidden-layer nodes for Hermite feed-forward neural networks
• Neural-network approximation of functions of several variables

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Principal component analysis in linear systems: Controllability, observability, and model reduction
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multilayer feedforward networks are universal approximators
• Approximation by superpositions of a sigmoidal function
• Title not available (Why is that?)

Cited In (10)

• Orthogonalisation procedure for training radial basis functions neural networks
• Properties and performance of orthogonal neural network in function approximation
• Higher Order Orthogonal Polynomials as Activation Functions in Artificial Neural Networks
• A mathematical discussion concerning the performance of multilayer perceptron-type artificial neural networks through use of orthogonal bipolar vectors
• Design of neural networks based on orthogonal experiments
• Artificial Intelligence and Soft Computing - ICAISC 2004
• Number determination of hidden-layer nodes for Hermite feed-forward neural networks
• Title not available (Why is that?)
• Title not available (Why is that?)
• Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation

This page was built for publication: Orthogonal considerations in the design of neural networks for function approximation.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q816796)