A new convex objective function for the supervised learning of single-layer neural networks

DOI10.1016/J.PATCOG.2009.11.024MaRDI QIDQ962791zbMATH OpenOpenAlexWikidataFDO

Authors Oscar Fontenla-Romero, Bertha Guijarro-Berdiñas, Beatriz Pérez-Sánchez, Amparo Alonso-Betanzos

Publication date 7 April 2010

Published in Pattern Recognition (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.patcog.2009.11.024

zbMATH Keywords

global optimumconvex optimizationleast squaresincremental learningsingle-layer neural networkssupervised learning method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• A Global Optimum Approach for One-Layer Neural Networks
• scientific article; zbMATH DE number 2033134
• scientific article; zbMATH DE number 1146238
• scientific article; zbMATH DE number 1234082
• Advances in Neural Networks – ISNN 2005

Cites work

• scientific article; zbMATH DE number 4211543 (Why is no real title available?)
• scientific article; zbMATH DE number 43066 (Why is no real title available?)
• scientific article; zbMATH DE number 1843268 (Why is no real title available?)
• scientific article; zbMATH DE number 3314813 (Why is no real title available?)
• A Global Optimum Approach for One-Layer Neural Networks
• Complexity of Solving Linear Systems in Different Models of Computation
• Fast recursive algorithms for a class of linear equations
• Multicategory proximal support vector machine classifiers
• Relative loss bounds for multidimensional regression problems

Cited in

(6)

• Ensemble decision forest of RBF networks via hybrid feature clustering approach for high-dimensional data classification
• Generalization bounds for non-stationary mixing processes
• Sequential complexities and uniform martingale laws of large numbers
• Nonlinear single layer neural network training algorithm for incremental, nonstationary and distributed learning scenarios
• Asymptotic sequential Rademacher complexity of a finite function class
• A joint optimization of momentum item and Levenberg-Marquardt algorithm to level up the BPNN's generalization ability

Describes a project that uses

Uses Software

• STPRTool
• UCI

This page was built for publication: A new convex objective function for the supervised learning of single-layer neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q962791)