Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing

DOI10.1016/J.AMC.2010.12.012MaRDI QIDQ628894zbMATH OpenOpenAlexFDO

Authors Chun-Cheng Peng, George D. Magoulas

Publication date 8 March 2011

Published in Applied Mathematics and Computation (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.amc.2010.12.012

zbMATH Keywords

BFGS updatesnonmonotone methodsquasi-Newton methodsrecurrent neural networkssecond-order training algorithmstemporal sequence

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of mathematical programming (90C90) Neural networks for/in biological studies, artificial life and related topics (92B20)

Recommendations

• Nonmonotone learning of recurrent neural networks in symbolic sequence processing applications
• scientific article; zbMATH DE number 7255038
• Recurrent Neural Networks Training Using Derivative Free Nonlinear Bayesian Filters
• A conjugate gradient learning algorithm for recurrent neural networks
• On the improvement of the real time recurrent learning algorithm for recurrent neural networks

Cites work

• A Family of Variable-Metric Methods Derived by Variational Means
• A new approach to variable metric algorithms
• A Nonmonotone Line Search Technique and Its Application to Unconstrained Optimization
• A Nonmonotone Line Search Technique for Newton’s Method
• A quasi-discrete Newton algorithm with a nonmonotone stabilization technique
• A Rapidly Convergent Descent Method for Minimization
• ADAPTIVE ALGORITHMS FOR NEURAL NETWORK SUPERVISED LEARNING: A DETERMINISTIC OPTIMIZATION APPROACH
• Analysis of a self-scaling quasi-Newton method
• Conditioning of Quasi-Newton Methods for Function Minimization
• Global convergence of nonmonotone descent methods for unconstrained optimization problems
• How bad are the BFGS and DFP methods when the objective function is quadratic?
• scientific article; zbMATH DE number 51537 (Why is no real title available?)
• scientific article; zbMATH DE number 1243473 (Why is no real title available?)
• scientific article; zbMATH DE number 1179315 (Why is no real title available?)
• scientific article; zbMATH DE number 1843095 (Why is no real title available?)
• scientific article; zbMATH DE number 938958 (Why is no real title available?)
• scientific article; zbMATH DE number 3294173 (Why is no real title available?)
• scientific article; zbMATH DE number 3308852 (Why is no real title available?)
• Numerical expirience with a class of self-scaling quasi-Newton algorithms
• On the alleviation of the problem of local minima in back-propagation
• Self-Scaling Variable Metric (SSVM) Algorithms
• Spatiotemporal connectionist networks: A taxonomy and review
• The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations
• Training the random neural network using quasi-Newton methods
• Variable Metric Method for Minimization

Cited in

(5)

• A novel method for speed training acceleration of recurrent neural networks
• Multi-stage ordinal optimization based approach for job shop scheduling problems
• Nonmonotone learning of recurrent neural networks in symbolic sequence processing applications
• Function Space BFGS Quasi-Newton Learning Algorithm for Time-Varying Recurrent Neural Networks
• An augmented Lagrangian method for training recurrent neural networks

This page was built for publication: Nonmonotone BFGS-trained recurrent neural networks for temporal sequence processing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q628894)