DocumentCode :
2971620
Title :
Learning and structuring of neural networks using genetic algorithm and linear programming
Author :
Nakayama, Hirotaka ; Iwata, Tadashi ; Yamauchi, Toshiyuki
Author_Institution :
Dept. of Appl. Math., Konan Univ., Kobe, Japan
Volume :
3
fYear :
1993
fDate :
25-29 Oct. 1993
Firstpage :
2702
Abstract :
Proposes a method for generating neural networks using genetic algorithms and linear programming; the genetic algorithm is used to decide the structure of neural net, while the linear programming is used for learning. This method holds a feature that there is no parameter sensitive to the speed and the precision of learning unlike the usual backpropagation. The effectiveness of the method is shown on the basis of several examples.
Keywords :
genetic algorithms; linear programming; neural nets; genetic algorithm; learning; linear programming; neural networks; structuring; Backpropagation; Genetic algorithms; Linear programming; Mathematics; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
Type :
conf
DOI :
10.1109/IJCNN.1993.714281
Filename :
714281
Link To Document :
بازگشت