Title :
A new indirect encoding method with variable length gene code to optimize neural network structures
Author :
Kobayashi, Kunikazu ; Ohbayashi, Masanao
Author_Institution :
Dept. of Comput. Sci. & Syst. Eng., Yamaguchi Univ., Japan
Abstract :
A new encoding method for optimizing neural network structures is proposed. It is based on an indirect encoding method with variable length gene code. The search ability for finding an optimal solution is higher than the direct encoding methods because redundant information in gene code is reduced and the search space is also reduced. The proposed method easily operates adding and deleting hidden units. The performance of the proposed method is evaluated through computer simulations
Keywords :
encoding; feedforward neural nets; optimisation; search problems; indirect encoding; multilayer neural network; search space; structure optimization; variable length gene code; Algorithm design and analysis; Computer science; Computer simulation; Electronic mail; Encoding; Genetic algorithms; Genetic mutations; Neural networks; Optimization methods; Systems engineering and theory;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.830879
