计算机工程2012,Vol.38Issue(20):164-168,5.DOI:10.3969/j.issn.1000-3428.2012.20.042
ELM算法中随机映射作用的实验研究
Experimental Research on Random Mapping Function in ELM Algorithm
摘要
Abstract
This paper studies the problem with experimental approach. It also investigates the impact of number of hidden layer nodes to generali2ation performance of Single Hidden Layer Feedforward Neural Network(SLFNN). Experiment on Extreme Learning Machine(ELM) with 35 databsets is made. For different databases, the optimal number of hidden layer nodes with respect to best test accuracy is found, and the performance of SLFKN can be improved by randomly mapping the data into a fixed high dimensional space with ELM algorithm.关键词
ELM算法/随机映射/神经网络/隐含层偏置/隐含层结点Key words
Extreme Learning Machine(ELM) algorithm/ random mapping/ neural network/ hidden layer bias/ hidden iayer node分类
信息技术与安全科学引用本文复制引用
翟俊海,李塔,翟梦尧,王熙照..ELM算法中随机映射作用的实验研究[J].计算机工程,2012,38(20):164-168,5.基金项目
国家自然科学基金资助项目(61170040) (61170040)
河北省自然科学基金资助项目(F2010000323,F2011201063,F2012201023) (F2010000323,F2011201063,F2012201023)
河北省高等学校科学技术研究基金资助重点项目(ZD2010139) (ZD2010139)
河北大学自然科学基金资助项目(2011-228043) (2011-228043)