中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Extreme learning machine with kernel model based on deep learning

文献类型：期刊论文

作者Ding, Shifei1,2; Guo, Lili1,2; Hou, Yanlu1,2
刊名NEURAL COMPUTING & APPLICATIONS
出版日期2017-08-01
卷号28期号:8页码:1975-1984
关键词Extreme learning machine (ELM) Deep-learning (DL) Convolutional neural network (CNN) CKELM
ISSN号0941-0643
DOI10.1007/s00521-015-2170-y
英文摘要Extreme learning machine (ELM) proposed by Huang et al. is a learning algorithm for single-hidden layer feedforward neural networks (SLFNs). ELM has the advantage of fast learning speed and high efficiency, so it brought into public focus. Later someone developed regularized extreme learning machine (RELM) and extreme learning machine with kernel (KELM). But they are the single-hidden layer network structure, so they have deficient in feature extraction. Deep learning (DL) is a multilayer network structure, and it can extract the significant features by learning from a lower layer to a higher layer. As DL mostly uses the gradient descent method, it will spend too much time in the process of adjusting parameters. This paper proposed a novel model of convolutional extreme learning machine with kernel (CKELM) which was based on DL for solving problems-KELM is deficient in feature extraction, and DL spends too much time in the training process. In CKELM model, alternate convolutional layers and subsampling layers add to hidden layer of the original KELM so as to extract features and classify. The convolutional layer and subsampling layer do not use the gradient algorithm to adjust parameters because of some architectures yielded good performance with random weights. Finally, we took experiments on USPS and MNIST database. The accuracy of CKELM is higher than ELM, RELM and KELM, which proved the validity of the optimization model. To make the proposed approach more convincing, we compared with other ELM-based methods and other DL methods and also achieved satisfactory results.
资助项目National Natural Science Foundation of China[61379101] ; National Key Basic Research Program of China[2013CB329502]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000405528300005
出版者SPRINGER
源URL[http://119.78.100.204/handle/2XEOYT63/7038]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Ding, Shifei
作者单位1.China Univ Min & Technol, Sch Comp Sci & Technol, Xuzhou 221116, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Ding, Shifei,Guo, Lili,Hou, Yanlu. Extreme learning machine with kernel model based on deep learning[J]. NEURAL COMPUTING & APPLICATIONS,2017,28(8):1975-1984.
APA Ding, Shifei,Guo, Lili,&Hou, Yanlu.(2017).Extreme learning machine with kernel model based on deep learning.NEURAL COMPUTING & APPLICATIONS,28(8),1975-1984.
MLA Ding, Shifei,et al."Extreme learning machine with kernel model based on deep learning".NEURAL COMPUTING & APPLICATIONS 28.8(2017):1975-1984.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。