A recalling-enhanced recurrent neural network: conjugate gradient learning algorithm and its convergence analysis

DOI10.1016/j.ins.2020.01.045zbMath1457.68233OpenAlexW3003573324WikidataQ120500310 ScholiaQ120500310MaRDI QIDQ2660959

Yanyan Li

Publication date: 31 March 2021

Published in: Information Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ins.2020.01.045

zbMATH Keywords

monotonicityconvergencerecurrent neural networkconjugate gradientgeneralized Armijo search

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

Deterministic convergence analysis via smoothing group Lasso regularization and adaptive momentum for Sigma-Pi-Sigma neural network

Uses Software

• UCI-ml

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A new class of nonlinear conjugate gradient coefficients with global convergence properties
• Efficient generalized conjugate gradient algorithms. I: Theory
• Convergence of gradient method for Eelman networks
• Assisted history matching for the inversion of fractures based on discrete fracture-matrix model with different combinations of inversion parameters
• Fully complex conjugate gradient-based neural networks using Wirtinger calculus framework: deterministic convergence and its application
• Minimization of functions having Lipschitz continuous first partial derivatives
• Generating chaos by an Elman network
• Training of Elman networks and dynamic system modelling
• A Nonlinear Conjugate Gradient Method with a Strong Global Convergence Property
• Function minimization by conjugate gradients
• Convergence Conditions for Ascent Methods
• Convergence Conditions for Ascent Methods. II: Some Corrections
• A spectral conjugate gradient method for unconstrained optimization