Error backpropagation using least absolute criterion

DOI10.1080/0020716042000301743MaRDI QIDQ4653710zbMATH OpenOpenAlexFDO

Authors S. H. Quah, Hong Choon Ong

Publication date 7 March 2005

Published in International Journal of Computer Mathematics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/0020716042000301743

zbMATH Keywords

Functional approximationL1 criterionMultilayer perceptron

Mathematics Subject Classification ID

Methods of quasi-Newton type (90C53)

Recommendations

• Advances in Neural Networks – ISNN 2005
• scientific article; zbMATH DE number 868047
• scientific article; zbMATH DE number 774008
• A modified backpropagation algorithm for training neural networks on data with error bars
• An improved error signal for the backpropagation model for classification problems

Cites work

• An Efficient Algorithm for Discrete $l_1$ Linear Approximation with Linear Constraints
• Approximation by superpositions of a sigmoidal function
• Combined LP and Quasi-Newton Methods for Nonlinear $l_1 $ Optimization
• Minimization Techniques for Piecewise Differentiable Functions: The l₁ Solution to an Overdetermined Linear System
• Multilayer feedforward networks are universal approximators

Cited in

(1)

• Advances in Neural Networks – ISNN 2005

This page was built for publication: Error backpropagation using least absolute criterion

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4653710)