摘要
针对进化神经网络中遗传算法收敛速度慢和容易早熟这两个难题,提出了一个启发性的变异算子.该算子采用了自适应的变异率和启发式的变异位的选择策略.在多代无进化时,通过提高变异率扩大搜索范围,同时减小变异量进行更细致的搜索.求解XOR问题的实验表明,该算法既具有很快的收敛速度又能自动维持群体的多样性.
In order to solve two difficult problems of premature convergence and slow searching speed of genetic algorithms in evolution neural network, a heuristic mutation operator is presented. Adaptive probability of mutation and heuristic mutation points selected is applied in it. When no evolution appears after many generations, the range of search will be extended by increasing probability of mutation, and a fine search will be started. The experiments of XOR problem demonstrate that the operator has fine ability of speedy convergence and maintains the diversity of the population automatically.
出处
《软件学报》
EI
CSCD
北大核心
2002年第4期726-731,共6页
Journal of Software
关键词
遗传算法
进化
神经网络
启发式变异算子
多样性
Convergence of numerical methods
Genetic algorithms
Heuristic methods
Mathematical operators
Probability
