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。
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 nor-mal 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.
出处
《计算机与现代化》
2015年第9期57-59,65,共4页
Computer and Modernization
关键词
蛙跳算法
粒子群算法
BP神经网络
shuffled frog leaping algorithm
particle swarm optimization algorithm
BP neural network
