中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Discriminative graph regularized broad learning system for image recognition

文献类型:期刊论文

作者Jin, Junwei1; Liu, Zhulin1; Chen, C. L. Philip1,2,3
刊名SCIENCE CHINA-INFORMATION SCIENCES
出版日期2018-11-01
卷号61期号:11页码:14
关键词broad learning system deep learning graph regularization image recognition feature extraction incremental learning
ISSN号1674-733X
DOI10.1007/s11432-017-9421-3
通讯作者Chen, C. L. Philip(philip.chen@ieee.org)
英文摘要Broad learning system (BLS) has been proposed as an alternative method of deep learning. The architecture of BLS is that the input is randomly mapped into series of feature spaces which form the feature nodes, and the output of the feature nodes are expanded broadly to form the enhancement nodes, and then the output weights of the network can be determined analytically. The most advantage of BLS is that it can be learned incrementally without a retraining process when there comes new input data or neural nodes. It has been proven that BLS can overcome the inadequacies caused by training a large number of parameters in gradient-based deep learning algorithms. In this paper, a novel variant graph regularized broad learning system (GBLS) is proposed. Taking account of the locally invariant property of data, which means the similar images may share similar properties, the manifold learning is incorporated into the objective function of the standard BLS. In GBLS, the output weights are constrained to learn more discriminative information, and the classification ability can be further enhanced. Several experiments are carried out to verify that our proposed GBLS model can outperform the standard BLS. What is more, the GBLS also performs better compared with other state-of-the-art image recognition methods in several image databases.
WOS关键词MULTILAYER FEEDFORWARD NETWORKS ; RESTRICTED BOLTZMANN MACHINE ; ROBUST FACE RECOGNITION ; TIME-SERIES PREDICTION ; FUNCTIONAL-LINK NET ; FUNCTION APPROXIMATION ; NEURAL-NETWORKS ; REPRESENTATION ; CLASSIFICATION
资助项目National Natural Science Foundation of China[61572540] ; Macau Science and Technology Development Fund (FDCT)[019/2015/A] ; Macau Science and Technology Development Fund (FDCT)[024/2015/AMJ] ; Macau Science and Technology Development Fund (FDCT)[079/2017/A2] ; University Macau MYR Grants
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:000447851800001
出版者SCIENCE PRESS
资助机构National Natural Science Foundation of China ; Macau Science and Technology Development Fund (FDCT) ; University Macau MYR Grants
源URL[http://ir.ia.ac.cn/handle/173211/28127]  
专题离退休人员
通讯作者Chen, C. L. Philip
作者单位1.Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China
2.Dalian Maritime Univ, Dalian 116026, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714
Jin, Junwei,Liu, Zhulin,Chen, C. L. Philip. Discriminative graph regularized broad learning system for image recognition[J]. SCIENCE CHINA-INFORMATION SCIENCES,2018,61(11):14.
APA Jin, Junwei,Liu, Zhulin,&Chen, C. L. Philip.(2018).Discriminative graph regularized broad learning system for image recognition.SCIENCE CHINA-INFORMATION SCIENCES,61(11),14.
MLA Jin, Junwei,et al."Discriminative graph regularized broad learning system for image recognition".SCIENCE CHINA-INFORMATION SCIENCES 61.11(2018):14.

入库方式: OAI收割

来源:自动化研究所

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。