Title :
Optimization with neural networks trained by evolutionary algorithms
Author :
Velazco, Marta I. ; Lyra, Christiano
Author_Institution :
Sch. of Electr. Eng. & Comput. Sci., State Univ. of Campinas, Brazil
fDate :
6/24/1905 12:00:00 AM
Abstract :
Multilayer neural networks are trained to solve optimization problems. Genetic algorithms are adopted to "evolve" weights, unveiling new points in the definition domain. As the evolution goes on, better points are found, driving the process to optimality. Case studies with convex and nonconvex problems illustrate the approach
Keywords :
concave programming; convex programming; feedforward neural nets; genetic algorithms; learning (artificial intelligence); mathematics computing; case studies; convex problems; definition domain; evolutionary algorithms; genetic algorithms; multilayer neural network training; nonconvex problems; optimization problems; weight evolution; Computer science; Evolutionary computation; Genetic algorithms; Hopfield neural networks; Logic; Merging; Multi-layer neural network; Network topology; Neural networks; Neurons;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1007742
