一种可应用于嵌入式系统的低复杂度超限学习机训练方法  

Low Complexity Training Strategy for Extreme Learning Machine Used in Embedded System

作　　者：张克终[1,2] 徐力 尉志青 黄赛[1] 冯志勇 ZHANG Ke-zhong;XU Li;WEI Zhi-qing;HUANG Sai;FENG Zhi-yong(School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China;Beijing Advanced Innovation Center for Future Internet Technology, Beijing University of Technology, Beijing 100124, China;Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China)

机构地区：[1]北京邮电大学信息与通信工程学院,北京100876 [2]北京工业大学北京未来网络科技高精尖创新中心,北京100124 [3]中国科学院计算技术研究所,北京100190

出　　处：《北京邮电大学学报》2018年第2期9-14,共6页Journal of Beijing University of Posts and Telecommunications

基　　金：国家自然科学基金项目(61631003,61525101);深圳市海外高层次人才创新创业专项资金“孔雀团队”项目(KQTD2015033114415450)

摘　　要：为解决超限学习机复杂度较高的问题,提出了一种新型的超限学习机更新策略,称为序列超限学习机.避免了复杂度较高的逆矩阵运算,而且能够应用于嵌入式系统中.序列超限学习机比各种广泛应用的机器学习分类器具有更低的计算复杂度.基于实际数据集的仿真结果表明,序列超限学习机的分类精度比传统超限学习机和其他广泛应用的分类器更高,而且具有更短的训练时间.Extreme learning machine（ ELM） achieves faster training speed and higher classification accuracy,compared with other widely used classifiers,such as back propagation（ BP）,support vector machine（ SVM）,spectral clustering（ SC）,and so forth. However,ELM suffers from some drawbacks： 1）ELM utilizes the calculation of inverse matrix for training,which cannot be adopted in the embedded system; 2） the training time of ELM increases dramatically for large-scale applications. To solve these drawbacks of ELM,a new training strategy called Sequential ELM（ SELM） was proposed,which avoids the calculation of inverse matrix. Therefore,SELM can be adopted in the embedded system. It is proven that SELM achieves lower complexity than other widely used algorithms. Furthermore,simulations based on practical datasets indicate that the classification accuracy of SELM is higher than traditional ELM and other widely used classifiers with shorter training time.

关 键 词：超限学习机 神经网络 分类算法 低复杂度 嵌入式系统 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]