| NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER |
| |
| 作者姓名： | 覃征 刘宇 王昱 |
| |
| 作者单位： | [1]Department of Computer Science and Technology, Xi＇an Jiaotong University, Xi＇an 710049, China [2]Department of Computer Science and Technology, Tsinghua University, Beij ing 100084, China |
| |
| 基金项目： | 国家重点基础研究发展计划(973计划) |
| |
| 摘 要： | Feed forward neural net works such as multi-layer perceptron,radial basis function neural net-works,have been widely applied to classification,function approxi mation and data mining.Evolu-tionary computation has been explored to train neu-ral net works as a very promising and competitive al-ternative learning method,because it has potentialto produce global mini mum in the weight space.Recently,an emerging evolutionary computationtechnique,Particle Swar m Opti mization(PSO)be-comes a hot to…
|
| 关 键 词： | 平行计算 神经网络 微粒群最优化 簇类 |
| 文章编号： | 1671-8267（2006）02-0109-04 |
NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER |
| |
| Qin Zheng,Liu Yu,Wang Yu.NEURAL NETWORK TRAINING WITH PARALLEL PARTICLE SWARM OPTIMIZER[J].Academic Journal of Xi’an Jiaotong University,2006,18(2):109-112. |
| |
| Authors: | Qin Zheng Liu Yu Wang Yu |
| |
| Abstract: | Objective To reduce the execution time of neural network training. Methods Parallel particle swarm optimization algorithm based on master-slave model is proposed to train radial basis function neural networks, which is implemented on a duster using MPI libraries for inter-process communication. Results High speed-up factor is achieved and execution time is reduced greatly. On the other hand, the resulting neural network has good classification accuracy not only on training sets but also on test sets. Conclusion Since the fitness evaluation is intensive, parallel particle swarm optimization shows great advantages to speed up neural network training. |
| |
| Keywords: | parallel computation neural network particle swarm optimization cluster |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
