计算机工程与应用2018，Vol.54Issue(2)：137-143,7.DOI:10.3778/j.issn.1002-8331.1608-0069
基于输入分片扰乱的BP神经网络MapReduce训练方法
摘要
Abstract
During the training of a BP neural network with MapReduce,its convergence with the current intermediate weight matrix is just got by sample data slices on the specific map task node.Therefore,the converge of the BP network to the whole training sample set is hard to be fulfilled.The approach to training BP networks with MapReduce based on sample slice disruptions is proposed.Based on systematic sampling to the whole training sample data,new input slice can be produced for each training map task.Such sample slices are used for the specific map tasks as new input during future training.This can accelerate the process of convergence of the BP network.Moreover,in order to speed up the local con-vergence of the map training tasks,the intermediate matrix with minimum global error is taken as the initial weight matrix during the future training.The experimental results on Hadoop clusters show that the approach can improve the efficiency of BP neural network training with MapReduce.关键词
神经网络/MapReduce/输入分片/收敛Key words
neural network/MapReduce/sample slices/convergence分类
信息技术与安全科学引用本文复制引用
陈旺虎,俞茂义,马生俊..基于输入分片扰乱的BP神经网络MapReduce训练方法[J].计算机工程与应用,2018,54(2):137-143,7.基金项目
国家自然科学基金(No.61462076) （No.61462076）
甘肃省自然科学基金(No.1104GKCA023) （No.1104GKCA023）
甘肃省科技攻关项目(No.1208RJZA134) （No.1208RJZA134）
西北师范大学青年教师科研提升计划(No.NWNU-LKQN-12-30). （No.NWNU-LKQN-12-30）
