| 综合改进的粒子群神经网络算法 |
| |
| 引用本文： | 何佳,陈智慧,杨迎新.综合改进的粒子群神经网络算法[J].计算机工程与设计,2008,29(11):2890-2892. |
| |
| 作者姓名： | 何佳 陈智慧 杨迎新 |
| |
| 作者单位： | 1. 河北理工大学,计算机与自动控制学院,电工电子教学实验中心,河北,唐山,063000
2. 河北理工大学,轻工学院,河北,唐山,063020 |
| |
| 摘 要： | 粒子群优化算法是一种解决非线性、不可微和多峰值复杂优化问题的优秀算法,但该算法在进化后期容易出现速度变慢以及早熟的现象;BP神经网络的学习算法是基于梯度下降这一本质的,因此存在着容易陷于局部极小值,收敛速度慢,训练时间长等问题.针对上述现象,对粒子群优化算法进行了增强粒子多样性和避免种群陷入早熟两个方面的改进,并提出了一种基于改进算法的粒子群神经网络算法,最后通过在IRIS数据集上进行的仿真实验验证了改进的有效性.
|
| 关 键 词： | 粒子群优化 神经网络 群智能 BP算法 粒子多样性 |
| 文章编号： | 1000-7024(2008)11-2890-03 |
| 修稿时间： | 2007年11月2日 |
Integrative improved particle swarm optimization neural network arithmetic |
| |
| HE Jia,CHEN Zhi-hui,YANG Ying-xin.Integrative improved particle swarm optimization neural network arithmetic[J].Computer Engineering and Design,2008,29(11):2890-2892. |
| |
| Authors: | HE Jia CHEN Zhi-hui YANG Ying-xin |
| |
| Affiliation: | HE Jia1,CHEN Zhi-hui2,YANG Ying-xin1 (1. Teaching , Experiment Center of Electrotechnics , Electronics,College of Computer , Automation,Hebei Polytechnic University,Tangshan 063000,China,2. College of Light Industry,Tangshan 063020,China) |
| |
| Abstract: | The particle swarm optimization arithmetic is an excellent optimization arithmetic that can solve the non-linear, un-fluxionary and multi-peak value optimizing problems. But in the process of looking for the excellent result, it is easily appear the phenomenon of speed becoming slow and precocious. The learning arithmetic of back propagation is base on the essence of grads descending, so there are inevitably problems of it is easy to get into partial least extremum, slowly constringency speed, long training... |
| |
| Keywords: | particle swarm optimization neural network swarm intelligence back propagation arithmetic multiformity of particles |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
