Novel training algorithm based on quadratic optimisation using neural networks

DOI10.1007/3-540-45720-8_48MaRDI QIDQ2781974zbMATH OpenFDO

Authors Ganesh Arulampalam, Abdesselam Bouzerdoum

Publication date 2 July 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/3-540-45720-8_48

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computing methodologies and applications (68U99)

Recommendations

• scientific article; zbMATH DE number 1054676
• A New Algorithm with a Line Search for Feedforward Neural Networks Training
• Quadratic optimization method for multilayer neural networks with local error-backpropagation
• A fast novel algorithm for neural networks
• Successive approximation training algorithm for feedforward neural networks

Cited in

(5)

• A neural network training algorithm utilizing multiple sets of linear equations
• New comprehensive learning method based on an LM-quasi-Newton algorithm applied to feed-forward neural networks
• Training multi-layered neural network with a trust-region based algorithm
• scientific article; zbMATH DE number 1054676 (Why is no real title available?)
• A New Algorithm with a Line Search for Feedforward Neural Networks Training

This page was built for publication: Novel training algorithm based on quadratic optimisation using neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2781974)