未找到相关数据
A New Method for Evolving Artificial Neural Networks Using Genetic Algorithm
被引：0
|作者：
Yan Wu
机构：
来源：
关键词：
neuroevolution;
genetic algorithm;
neural network;
niching method;
D O I：
暂无
中图分类号：
TP183 [人工神经网络与计算];
学科分类号：
081104 ;
0812 ;
0835 ;
1405 ;
摘要：
In this paper, a new neuroevolution algorithm (NEGA) for simultaneous evolution of both architectures and weights of neural networks is described. A whole new network encoding method is shown. The competing conventions problem is solved absolutely. Heuristic methods are used to constrain the topology mutation probability and the trend of mutation kind choice. Also, the niching method is used to protect the network topologies evolution. The experiment results show the efficiency and rapidity of NEGA forcefully.
引用
收藏
页码：79 / 82
页数：4
相关论文