摘要： 基于Map Reduce框架的传统BP神经网络算法收敛缓慢，训练易陷入局部极小点，使迭代次数过多，极大浪费资源。为此，提出并实现改进的并行BP算法，采用动态调节学习率、动量因子调整权重修正值，提升BP网络并行训练效率，利用预处理数据和最大分类概率增强分类的准确性。实验结果表明，改进的并行算法能提高分类准确率，缩短近17/18的训练时间。

关键词: 神经网络, 改进反向传播算法, Map Reduce架构, 并行, 学习率, 动量因子

Abstract: The traditional algorithm of BP neural network based on Map Reduce framework has been researched. But the convergence speed of traditional BP algorithm is quite slow. The training is easily into local minimum spot. The iterations of processing training data are quite frequency, a great waste of resources. The proposed design thus parallels the improved BP neural network based on Map Reduce. The adjustment of self-adaptive learning rate and momentum factors are implemented in this design. The proposed design also uses maximum classification probability factor and preprocess method to enhance the correctness. Experimental result shows that improved parallel algorithm costs 17 times shorter than the primary. The accuracy is also improved further.

Key words: neural network, improved Back Propagation(BP) algorithm, Map Reduce architecture, parallel, learning rate, momentum factor

中图分类号: 

• TP387