改进的萤火虫算法在神经网络中的应用  

Application of improved firefly algorithm in neural network

作　　者：张明[1] 张树群[1] 雷兆宜[1] ZHANG Ming;ZHANG Shuqun;LEI Zhaoyi(College of Information Science and Technology, Jinan University, Guangzhou 510632, China)

机构地区：[1]暨南大学信息科学与技术学院,广州510632

出　　处：《计算机工程与应用》2017年第5期159-163,共5页Computer Engineering and Applications

摘　　要：基本萤火虫算法存在容易陷入局部最优及收敛速度低的问题,提出了一种改进进化机制的萤火虫算法(IEMFA)。在群体进化过程中赋予萤火虫改进的位置移动策略,并利用改进后的萤火虫算法来优化传统BP神经网络的网络参数。测试结果表明,基于改进萤火虫算法的BP神经网络具有更好的收敛速度和精度。Basic Firefly Algorithm(FA)has some bugs such that it is easy to fall into local optimum and the slow convergence speed. In order to overcome these shortcomings, the paper puts forward a Firefly Algorithm with Improved EvolutionMechanism(IEMFA). The proposed algorithm is used to optimize the weight value of BP neural network and the result shows that the algorithm expedites the convergence rate, improves the precision and has a better global searching ability.

关 键 词：进化机制 误差反向传播(BP)神经网络 萤火虫算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]