Title :
The method of design for MLPNN´s structure based on species evolutionary GA
Author :
Zhiyong, Li ; Tiaosheng, Tong ; Liang, Jiang
Author_Institution :
Coll. of Electr. & Inf. Eng., Hunan Univ., Changsha, China
Abstract :
In dealing with the design of neural network´s structure and drawbacks of the normal design methods, this paper proposes a new method for designing the multilayer perceptron neural network (MLPNN) structure based on species evolutionary genetic algorithms. This method of combining the neural network (NN) and genetic algorithm (GA) has the superiority of NN´s structure training speed and fitness. The simulation and application demonstrate the effectiveness of the method
Keywords :
genetic algorithms; learning (artificial intelligence); multilayer perceptrons; genetic algorithms; multilayer perceptron; neural network; species evolution; structure learning; Algorithm design and analysis; Design engineering; Design methodology; Educational institutions; Genetic algorithms; Genetic engineering; Neural networks;
Conference_Titel :
Intelligent Control and Automation, 2000. Proceedings of the 3rd World Congress on
Conference_Location :
Hefei
Print_ISBN :
0-7803-5995-X
DOI :
10.1109/WCICA.2000.863365
