Abstract: An artificial bee colony algorithm based on foraging behavior of honeybee swarms is proposed to improve the traditional BP neural network algorithm. The developed algorithm has the characters of both heuristic bionics and swarm intelligence. It is a global optimum algorithm and convenient for practical use. The proposed algorithm is used to optimize the weight value of BP neural network and the obtained results show that the algorithm really improves both the precision and the convergence rate.

Key words: Back Propagation（BP） neural network, artificial bee colony algorithm, adaptive

摘要： 人工蜂群算法是模拟蜜蜂采蜜行为而提出的一种新的启发式仿生算法，属于典型的群体智能算法。提出了一种改进的人工蜂群算法，并利用改进后的人工蜂群算法来优化传统BP算法（神经网络算法中的误差方向传播算法）中网络参数的权值。实验结果证明该优化算法提高了BP神经网络收敛解的精度，加快了BP神经网络收敛速度。

关键词: 反向传播（BP）神经网络, 人工蜂群算法, 自适应