Title :
New Discrete-Time Recurrent Neural Network Proposal for Quadratic Optimization With General Linear Constraints
Author :
Perez-Ilzarbe, M.J.
Author_Institution :
Dept. de Autom. y Comput., Univ. Publica de Navarra, Pamplona, Spain
Abstract :
In this brief, the quadratic problem with general linear constraints is reformulated using the Wolfe dual theory, and a very simple discrete-time recurrent neural network is proved to be able to solve it. Conditions that guarantee global convergence of this network to the constrained minimum are developed. The computational complexity of the method is analyzed, and experimental work is presented that shows its high efficiency.
Keywords :
computational complexity; convergence; mathematics computing; quadratic programming; recurrent neural nets; Wolfe dual theory; computational complexity; discrete-time recurrent neural network; general linear constraint; global convergence; quadratic optimization; Bismuth; Computational modeling; Convergence; Learning systems; Optimization; Trajectory; Vectors; Discrete time; global convergence; hybrid constraints; neural networks; quadratic optimization;
Journal_Title :
Neural Networks and Learning Systems, IEEE Transactions on
DOI :
10.1109/TNNLS.2012.2223484
