Convergence of gradient method for a fully recurrent neural network

DOI10.1007/s00500-009-0398-0zbMath1191.68540OpenAlexW2049463817MaRDI QIDQ2380334

Wei Wu, Zheng-xue Li, Dong-po Xu

Publication date: 26 March 2010

Published in: Soft Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00500-009-0398-0

zbMATH Keywords

monotonicityconvergencefully recurrent neural networkgradient descent learning algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Discrete time-variant nonlinear optimization and system solving via integral-type error function and twice ZND formula with noises suppressed ⋮ Application of neural networks to inverse elastic scattering problems with near-field measurements ⋮ Convergence Analysis of Three Classes of Split-Complex Gradient Algorithms for Complex-Valued Recurrent Neural Networks ⋮ Convergence of gradient method for Eelman networks ⋮ A neural network method for the inverse scattering problem of impenetrable cavities ⋮ A neural network scheme for recovering scattering obstacles with limited phaseless far-field data

Cites Work

• Unnamed Item
• Sufficient Conditions for Error Backflow Convergence in Dynamical Recurrent Neural Networks

This page was built for publication: Convergence of gradient method for a fully recurrent neural network