An independent component analysis based weight initialization method for multilayer perceptrons

DOI10.1016/S0925-2312(01)00674-9MaRDI QIDQ1852024zbMATH OpenOpenAlexFDO

Authors Yat-Fung Yam, C.-T. Leung, P. K. S. Tam, W. C. Siu

Publication date 9 January 2003

Published in Neurocomputing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/s0925-2312(01)00674-9

zbMATH Keywords

Independent component analysisMultilayer perceptronsWeight initialization

Mathematics Subject Classification ID

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

Recommendations

• New weight learning strategy for fully connected feedforward neural networks
• Evolving multilayer perceptrons
• Structural, Syntactic, and Statistical Pattern Recognition
• Algorithm of choosing initialized weights for training complex-valued neural networks
• Training multilayer perceptrons by principal component analysis

Cited in

(10)

• Connection between multilayer perceptrons and regression using independent component analysis
• New weight learning strategy for fully connected feedforward neural networks
• scientific article; zbMATH DE number 1849134 (Why is no real title available?)
• New Approach of Recurrent Neural Network Weight Initialization
• Algorithm of choosing initialized weights for training complex-valued neural networks
• Structural, Syntactic, and Statistical Pattern Recognition
• scientific article; zbMATH DE number 1728406 (Why is no real title available?)
• A fractional gradient descent algorithm robust to the initial weights of multilayer perceptron
• scientific article; zbMATH DE number 1784881 (Why is no real title available?)
• Solving the linear interval tolerance problem for weight initialization of neural networks

This page was built for publication: An independent component analysis based weight initialization method for multilayer perceptrons

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1852024)