Nonlinear dynamical system modeling via recurrent neural networks and a weighted state space search algorithm

DOI10.3934/JIMO.2011.7.385zbMATH Open1221.68197OpenAlexW2090203704MaRDI QIDQ549896FDOQ549896

Ka Fai Cedric Yiu, Sally Shao, Leong Kwan Li

Publication date: 19 July 2011

Published in: Journal of Industrial and Management Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.3934/jimo.2011.7.385

Recommendations

• A state space search algorithm and its application to learn the short-term foreign exchange rates
• Convergence analysis of the weighted state space search algorithm for recurrent neural networks
• scientific article; zbMATH DE number 5139255
• Recurrent Neural Networks Training Using Derivative Free Nonlinear Bayesian Filters
• Mechanical system modelling using recurrent neural networks via quasi- Newton learning methods

zbMATH Keywords

nonlinear dynamical systemrecurrent neural networklearning algorithmstate space search

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Numerical methods for mathematical programming, optimization and variational techniques (65K99)

Cited In (4)

• Learning nonlinear state-space models using autoencoders
• Training recurrent neural networks by sequential least squares and the alternating direction method of multipliers
• Convergence analysis of the weighted state space search algorithm for recurrent neural networks
• A state space search algorithm and its application to learn the short-term foreign exchange rates

This page was built for publication: Nonlinear dynamical system modeling via recurrent neural networks and a weighted state space search algorithm

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q549896)