| 基于MapReduce的BP神经网络算法研究 |
| |
| 引用本文： | 朱晨杰,杨永丽.基于MapReduce的BP神经网络算法研究[J].微型电脑应用,2012,28(10):9-12,19. |
| |
| 作者姓名： | 朱晨杰 杨永丽 |
| |
| 作者单位： | 1. 上海交通大学软件学院,上海,200240
2. 91999部队,青岛,266003 |
| |
| 摘 要： | 随着信息化社会的飞速发展,需要进行数据挖掘的数据量急剧增大,传统的串行化BP神经网络训练方法在处理海量数据集时存在很大问题,如耗时过长,甚至内存不足无法训练。为了解决这个问题,提出了一种在云计算环境下,基于MapReduce的BP神经网络训练方法 MR-GAIBP,实验证明,提出的方法,相比于已有的方法拥有更快的收敛速度和更高的精度,在大数据集上有更快的训练速度。
|
| 关 键 词： | BP神经网络 MapReduce 遗传算法 |
Research of MapReduce Based on BP Neural Network Algorithm |
| |
| Zhu Chenjie
,
Yang Yongli.Research of MapReduce Based on BP Neural Network Algorithm[J].Microcomputer Applications,2012,28(10):9-12,19. |
| |
| Authors: | Zhu Chenjie Yang Yongli |
| |
| Affiliation: | 1.Shanghai Jiao Tong University, Shanghai200240, China; 2.91999 PLA Troops, Qingdao266003, China) |
| |
| Abstract: | With the rapid development of the information society, huge amounts of data are produced every day. The traditional training method of BP neural network will encounter many problems, such as costing too much time and leading to insufficient memory. To solve these problems, this paper proposes a new parallel training method that is based on MapReduce. Experiment results demonstrate that the convergence rate is faster and accuracy is higher. |
| |
| Keywords: | BP Neural Network MapReduce Genetic Algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
