A new learning method using prior information of neural networks

MaRDI QIDQ866134zbMATH OpenFDO

Authors Baiguan Lü, Junichi Murata, Kotaro Hirasawa

Publication date 20 February 2007

Published in Science in China. Series F (Search for Journal in Brave)

Full work available at URL http://hdl.handle.net/2324/1498417

zbMATH Keywords

exact mathematical structureneural network learningpart parameter learningprior information

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Identification in stochastic control theory (93E12)

Recommendations

• Using Prior Information to Improve the Approximation Performances of Neural Networks
• A noninformative prior for neural networks
• Prior knowledge for learning networks in non-probabilistic settings

Cited in

(3)

• Prior knowledge for learning networks in non-probabilistic settings
• Reuse of information in multi-layer sigma-pi neural networks
• Using Prior Information to Improve the Approximation Performances of Neural Networks

This page was built for publication: A new learning method using prior information of neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q866134)