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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 多媒体计算与图形学团队
Two-Phase Construction of Multilayer Perceptrons Using Information Theory

文献类型：期刊论文

作者Xing, Hong-Jie1; Hu, Bao-Gang2
刊名IEEE TRANSACTIONS ON NEURAL NETWORKS
出版日期2009-04-01
卷号20期号:4页码:715-721
关键词Hidden units pruning input units selection multilayer perceptron (MLP) mutual information (MI) criterion
英文摘要This brief presents a two-phase construction approach for pruning both input and hidden units of multilayer perceptrons (MLPs) based on mutual information (MI). First, all features of input vectors are ranked according to their relevance to target outputs through a forward strategy. The salient input units of an MLP are thus determined according to the order of the ranking result and by considering their contributions to the network's performance. Then, the irrelevant features of input vectors can be identified and eliminated. Second, the redundant hidden units are removed from the trained MLP one after another according to a novel relevance measure. Compared with its related work, the proposed strategy exhibits better performance. Moreover, experimental results show that the proposed method is comparable or even superior to support vector machine (SVM) and support vector regression (SVR). Finally, the advantages of the MI-based method are investigated in comparison with the sensitivity analysis (SA)-based method.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic
研究领域[WOS]Computer Science ; Engineering
关键词[WOS]REGRESSION ; SELECTION
收录类别SCI
语种英语
WOS记录号WOS:000265376200013
源URL[http://ir.ia.ac.cn/handle/173211/2817]  
专题自动化研究所_模式识别国家重点实验室_多媒体计算与图形学团队
作者单位1.Hebei Univ, Coll Math & Comp Sci, Baoding 071002, Peoples R China
2.Chinese Acad Sci, Natl Lab Pattern Recognit, Inst Automat, Beijing 1000910, Peoples R China
推荐引用方式
GB/T 7714		 Xing, Hong-Jie,Hu, Bao-Gang. Two-Phase Construction of Multilayer Perceptrons Using Information Theory[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS,2009,20(4):715-721.
APA Xing, Hong-Jie,&Hu, Bao-Gang.(2009).Two-Phase Construction of Multilayer Perceptrons Using Information Theory.IEEE TRANSACTIONS ON NEURAL NETWORKS,20(4),715-721.
MLA Xing, Hong-Jie,et al."Two-Phase Construction of Multilayer Perceptrons Using Information Theory".IEEE TRANSACTIONS ON NEURAL NETWORKS 20.4(2009):715-721.

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。