摘要
提出一种用改进的遗传算法优化神经网络的方法,即在遗传算法进化过程中,对适应度函数值标定,并采用期望值选择法进行选择操作,然后用这种遗传算法来优化神经网络权值。将该改进的遗传算法应用于入侵检测中。实验结果表明,用这种改进的遗传算法优化后的神经网络算法在防止局部收敛方面更加有效。
In this paper,an improved genetic algorithm that optimizes neural network is proposed,which is used to scale the fitness function and select the proper operation according to the expected value in the course of optimization,and then the weights of neural network is optimized.This method is applied to the intrusion detection.The result shows that the neural network optimized by this improved genetic algorithm is more effective than that unoptimized by this algorithm.
出处
《遥测遥控》
2008年第1期51-54,共4页
Journal of Telemetry,Tracking and Command
关键词
BP神经网络
遗传算法
权值
标定
期望值
BP neural network
Genetic algorithm
Weight
Scale
Expected value
