Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks

DOI10.1016/S0925-2312(01)00654-3MaRDI QIDQ1851972zbMATH OpenOpenAlexFDO

Authors Romuald Boné, Michel Crucianu, Jean-Pierre Asselin de Beauville

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)00654-3

zbMATH Keywords

Recurrent networksConstructive algorithmsLong-term dependenciesTime-delayed connections

Mathematics Subject Classification ID

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

Recommendations

• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions
• Temporal-kernel recurrent neural networks
• Bayesian learning for recurrent neural networks
• scientific article; zbMATH DE number 7714085
• Implicit sequence learning in recurrent neural networks

Cited in

(8)

• scientific article; zbMATH DE number 1843091 (Why is no real title available?)
• scientific article; zbMATH DE number 7714085 (Why is no real title available?)
• scientific article; zbMATH DE number 1843089 (Why is no real title available?)
• Bayesian learning for recurrent neural networks
• Temporal-kernel recurrent neural networks
• Embedding connectionist autonomous agents in time: The `road sign problem'
• Implicit sequence learning in recurrent neural networks
• The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions

This page was built for publication: Learning long-term dependencies by the selective addition of time-delayed connections to recurrent neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1851972)