Second-order stagewise backpropagation for Hessian-matrix analyses and investigation of negative curvature

DOI10.1016/j.neunet.2007.12.038zbMath1254.68214OpenAlexW2066516623WikidataQ51893052 ScholiaQ51893052MaRDI QIDQ1931996

Stuart E. Dreyfus, Eiji Mizutani

Publication date: 17 January 2013

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2007.12.038

zbMATH Keywords

negative curvaturetrust-region methodsindefinite Hessian matrixstagewise second-order backpropagation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items (1)

A matrix-free line-search algorithm for nonconvex optimization

Cites Work

• The local minima of the error surface of the \(2-2-1\) XOR network
• Separable nonlinear least squares: the variable projection method and its applications
• Trust Region Methods
• Ill-Conditioning in Neural Network Training Problems
• Singularities Affect Dynamics of Learning in Neuromanifolds
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Second-order stagewise backpropagation for Hessian-matrix analyses and investigation of negative curvature