热门
Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture
文献类型：期刊论文
| 作者 | Chen, C. L. Philip1,2,3; Liu, Zhulin3 |
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2018 |
| 卷号 | 29期号:1页码:10-24 |
| 关键词 | Big data big data modeling broad learning system (BLS) deep learning incremental learning random vector functional-link neural networks (RVFLNN) single layer feedforward neural networks (SLFN) singular value decomposition (SVD) |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2017.2716952 |
| 通讯作者 | Chen, C. L. Philip(philip.chen@ieee.org) |
| 英文摘要 | Broad Learning System (BLS) that aims to offer an alternative way of learning in deep structure is proposed in this paper. Deep structure and learning suffer from a time-consuming training process because of a large number of connecting parameters in filters and layers. Moreover, it encounters a complete retraining process if the structure is not sufficient to model the system. The BLS is established in the form of a flat network, where the original inputs are transferred and placed as "mapped features" in feature nodes and the structure is expanded in wide sense in the "enhancement nodes." The incremental learning algorithms are developed for fast remodeling in broad expansion without a retraining process if the network deems to be expanded. Two incremental learning algorithms are given for both the increment of the feature nodes (or filters in deep structure) and the increment of the enhancement nodes. The designed model and algorithms are very versatile for selecting a model rapidly. In addition, another incremental learning is developed for a system that has been modeled encounters a new incoming input. Specifically, the system can be remodeled in an incremental way without the entire retraining from the beginning. Satisfactory result for model reduction using singular value decomposition is conducted to simplify the final structure. Compared with existing deep neural networks, experimental results on the Modified National Institute of Standards and Technology database and NYU NORB object recognition dataset benchmark data demonstrate the effectiveness of the proposed BLS. |
| WOS关键词 | FUNCTIONAL-LINK NET ; NEURAL-NETWORKS ; ALGORITHM ; SELECTION ; REPRESENTATION ; APPROXIMATION ; REGRESSION ; SHRINKAGE |
| 资助项目 | Macao Science and Technology Development Fund[019/2015/A1] ; UM Research Grants ; National Nature Science Foundation of China[61572540] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000419558900002 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Macao Science and Technology Development Fund ; UM Research Grants ; National Nature Science Foundation of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/28278]  |
| 专题 | 离退休人员 |
| 通讯作者 | Chen, C. L. Philip |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China 2.Dalian Maritime Univ, Dalian 116026, Peoples R China 3.Univ Macau, Fac Sci & Technol, Dept Comp & Informat Sci, Macau 99999, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, C. L. Philip,Liu, Zhulin. Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2018,29(1):10-24. |
| APA | Chen, C. L. Philip,&Liu, Zhulin.(2018).Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,29(1),10-24. |
| MLA | Chen, C. L. Philip,et al."Broad Learning System: An Effective and Efficient Incremental Learning System Without the Need for Deep Architecture".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 29.1(2018):10-24. |
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。