Knowledge Commons of Institute of Automation,CAS
Generative and Discriminative Fuzzy Restricted Boltzmann Machine Learning for Text and Image Classification | |
Chen, C. L. Philip1,2,3; Feng, Shuang1,4 | |
发表期刊 | IEEE TRANSACTIONS ON CYBERNETICS |
ISSN | 2168-2267 |
2020-05-01 | |
卷号 | 50期号:5页码:2237-2248 |
通讯作者 | Feng, Shuang(fengshuang@bnuz.edu.cn) |
摘要 | The restricted Boltzmann machine (RBM) is an excellent generative learning model for feature extraction. By extending its parameters from real numbers to fuzzy ones, we have developed the fuzzy RBM (FRBM) which is demonstrated to possess better generative capability than RBM. In this paper, we first propose a generative model named Gaussian FRBM (GFRBM) to deal with real-valued inputs. Then, motivated by the fact that the discriminative variant of RBM can provide a self-contained framework for classification with competitive performance compared with some traditional classifiers, we establish the discriminative FRBM (DFRBM) and discriminative GFRBM (DGFRBM) that combine both the generative and discriminative facility by adding extra neurons next to the input units. Specifically, they can be trained into excellent stand-alone classifiers and retain outstanding generative capability simultaneously. The experimental results including text and image (both clean and noisy) classification indicate that DFRBM and DGFRBM outperform discriminative RBM models in terms of reconstruction and classification accuracy, and they behave more stable when encountering noisy data. Moreover, the proposed learning models show some promising advantages over other standard classifiers. |
关键词 | Data models Training Neurons Image reconstruction Feature extraction Computational modeling Cybernetics Discriminative learning fuzzy number Gaussian fuzzy restricted Boltzmann machine (GFRBM) image classification |
DOI | 10.1109/TCYB.2018.2869902 |
关键词[WOS] | POSSIBILISTIC MEAN-VALUE ; NEURAL-NETWORK ; RECOGNITION ; SYSTEMS ; LOGIC |
收录类别 | SCI |
语种 | 英语 |
资助项目 | National Natural Science Foundation of China[61751202] ; National Natural Science Foundation of China[61751205] ; National Natural Science Foundation of China[61572540] ; Macau Science and Technology Development Fund (FDCT)[019/2015/A1] ; Macau Science and Technology Development Fund (FDCT)[079/2017/A2] ; Macau Science and Technology Development Fund (FDCT)[024/2015/AMJ] ; MYRG of University of Macau ; Teacher Research Capacity Promotion Program of Beijing Normal University, Zhuhai |
项目资助者 | National Natural Science Foundation of China ; Macau Science and Technology Development Fund (FDCT) ; MYRG of University of Macau ; Teacher Research Capacity Promotion Program of Beijing Normal University, Zhuhai |
WOS研究方向 | Automation & Control Systems ; Computer Science |
WOS类目 | Automation & Control Systems ; Computer Science, Artificial Intelligence ; Computer Science, Cybernetics |
WOS记录号 | WOS:000528622000039 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/39360 |
专题 | 离退休人员 |
通讯作者 | Feng, Shuang |
作者单位 | 1.Univ Macau, Fac Sci & Technol, Macau 999078, Peoples R China 2.Dalian Maritime Univ, Dept Nav, Dalian 116026, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China 4.Beijing Normal Univ, Sch Appl Math, Zhuhai 519087, Peoples R China |
第一作者单位 | 中国科学院自动化研究所 |
推荐引用方式 GB/T 7714 | Chen, C. L. Philip,Feng, Shuang. Generative and Discriminative Fuzzy Restricted Boltzmann Machine Learning for Text and Image Classification[J]. IEEE TRANSACTIONS ON CYBERNETICS,2020,50(5):2237-2248. |
APA | Chen, C. L. Philip,&Feng, Shuang.(2020).Generative and Discriminative Fuzzy Restricted Boltzmann Machine Learning for Text and Image Classification.IEEE TRANSACTIONS ON CYBERNETICS,50(5),2237-2248. |
MLA | Chen, C. L. Philip,et al."Generative and Discriminative Fuzzy Restricted Boltzmann Machine Learning for Text and Image Classification".IEEE TRANSACTIONS ON CYBERNETICS 50.5(2020):2237-2248. |
条目包含的文件 | 条目无相关文件。 |
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。
修改评论