DocumentCode
1684671
Title
Function optimization by RPLNN
Author
Menhaj, Mohammad B. ; Seifipour, Navid
Author_Institution
Dept. of Electr. Eng., Amirkabir Univ. of Technol., Tehran, Iran
Volume
2
fYear
2002
fDate
6/24/1905 12:00:00 AM
Firstpage
1522
Lastpage
1527
Abstract
This paper introduces a model-free optimization method, called ring probabilistic logic neural networks (RPLNNs), for function optimization. In order to compare the performance of RPLNNs with that of conventional genetic algorithms (CGAs), two different optimization problems have been considered. The simulation results show that the RPLNN remarkably outperforms the CGA and some gradient-based methods as well
Keywords
functional analysis; mathematics computing; neural nets; optimisation; performance evaluation; probabilistic logic; function optimization; genetic algorithms; gradient-based methods; model-free optimization method; performance; ring probabilistic logic neural networks; simulation; Genetic algorithms; Iterative algorithms; Iterative methods; Neural networks; Neurons; Optimization methods; Probabilistic logic; Search methods; Simulated annealing; Solids;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location
Honolulu, HI
ISSN
1098-7576
Print_ISBN
0-7803-7278-6
Type
conf
DOI
10.1109/IJCNN.2002.1007743
Filename
1007743
Link To Document