计算机与现代化

• 算法设计与分析 • 上一篇    下一篇

基于蛙跳粒子群的BP神经网络算法

  

  1. 1.中国地质大学(北京)信息工程学院,北京100083;2.中国国土资源航空物探遥感中心,北京100083
  • 收稿日期:2015-07-13 出版日期:2015-09-21 发布日期:2015-09-24
  • 作者简介:谷全宇(1990-),男,黑龙江绥化人,中国地质大学(北京)信息工程学院硕士研究生,研究方向:计算机网络,智能控制; 张梦婷(1986-),女,中国国土资源航空物探遥感中心,硕士,研究方向:计算机网 络,信息通信,智能控制。

 BP Neural Network Algorithm Based on Frog Leaping Particle Swarm Optimization

  1. 1. Information Engineering Institute, China University of Geosciences, Beijing 100083, China;

     2. China Aero Geophysical Survey and Remote Sensing Center for Land and Resources, Beijing 100083, China
  • Received:2015-07-13 Online:2015-09-21 Published:2015-09-24

摘要:

 针对BP神经网络算法计算量复杂、收敛速度缓慢等缺点,提出一种基于启发式算法的BP神经网络权值和阈值的迭代方法。该方法结合蛙跳粒子群可控参数少、收敛速度快等特点,将神经网
络权值和阈值作为粒子,通过粒子更新来实现BP神经网络训练。实验结果表明,该算法的精度可在1.5342e-03左右。

关键词:  , 蛙跳算法, 粒子群算法, BP神经网络

Abstract:

In order to solve the problems that the calculation of BP neural network is very complex and its convergence rate is slow, an iterative method of weight and
threshold of the BP neural network based on the heuristic algorithm is put forward. This method combined with two advantages of the Frog Leaping Particle Swarm, in which, one is
less controllable parameter than normal ways and the other one is the fast convergence speed. In essence, the weight and the threshold of neural network can be seen as
particles. BP neural network was trained by particle updating and the accuracy of the algorithm is about 1.5342e-03.

Key words: shuffled frog leaping algorithm, particle swarm optimization algorithm, BP neural network