Title :
A time-varying recurrent neural system for convex programming
Author_Institution :
Dept. of Ind. Technol., North Dakota Univ., Grand Forks, ND, USA
Abstract :
The asymptotic stability of a recurrent neural network with monotonically time-varying penalty parameter for optimization is theoretically justified. The conditions of feasibility of solutions generated by the recurrent neural networks are characterized. The conditions of optimality of solutions to convex programming problems generated by the recurrent neural networks are characterized. The design methodology of the operating characteristics of the recurrent neural networks are presented by illustrative examples
Keywords :
convex programming; neural nets; stability; time-varying systems; asymptotic stability; convex programming; design methodology; monotonically time-varying penalty parameter; operating characteristics; optimality conditions; optimization; recurrent neural network; solution feasibility conditions; Asymptotic stability; Character generation; Design methodology; Functional programming; Neodymium; Recurrent neural networks; Stability analysis; Sufficient conditions; Time varying systems; Traveling salesman problems;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155166
