Sufficient Conditions for Error Backflow Convergence in Dynamical Recurrent Neural Networks

DOI10.1162/089976602760128063zbMATH Open1010.68113OpenAlexW2109565492WikidataQ52034613 ScholiaQ52034613MaRDI QIDQ3149526FDOQ3149526

Authors: Alex Aussem 

Publication date: 25 September 2002

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

Full work available at URL: https://doi.org/10.1162/089976602760128063

Recommendations

• scientific article; zbMATH DE number 2156307
• Convergence of gradient method for a fully recurrent neural network
• scientific article; zbMATH DE number 2033186
• Stable and convergent dynamics for discrete-time recurrent networks
• Analysis of gradient descent learning algorithms for multilayer feedforward neural networks

zbMATH Keywords

filtersfinite impulsive response

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (3)

• Title not available (Why is that?)
• Convergence of gradient method for a fully recurrent neural network
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions

This page was built for publication: Sufficient Conditions for Error Backflow Convergence in Dynamical Recurrent Neural Networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3149526)