Adaptive training and pruning for neural networks: algorithms and application
文献类型：期刊论文
| 作者 | Chen, S; Chang, SJ; Yuan, JH; Zhang, YX; Wong, KW |
| 刊名 | ACTA PHYSICA SINICA
 |
| 出版日期 | 2001-04-01 |
| 卷号 | 50页码:674-681 |
| 关键词 | neural networks pattern recognition extended Kalman filtering pruning |
| ISSN号 | 1000-3290 |
| 英文摘要 | Finding an optimal network size is one of the major concerns when building a neural network. In using the local extended Kalman filter (EKF) algorithm, we propose an efficient approach that combines EKF training and pruning as a whole. In particular, the covariance matrix obtained along with the local EKF training can be utilized to indicate the importance of the network weights. As a result, the network size can be determined adaptively to keep pace with the changes in input characteristics. The effectiveness of this algorithm is demonstrated on generalized XOR logic function and handwritten digit recognition. |
| WOS研究方向 | Physics |
| 语种 | 英语 |
| WOS记录号 | WOS:000167947700017 |
| 出版者 | CHINESE PHYSICAL SOC |
| 源URL | [http://119.78.100.186/handle/113462/37014]  |
| 专题 | 中国科学院近代物理研究所 |
| 通讯作者 | Chen, S |
| 作者单位 | 1.Nankai Univ, Inst Modern Phys, Lab Opt Informat Sci, Chinese Minist Educ, Tianjin 300071, Peoples R China 2.City Univ Hong Kong, Dept Elect Engn, Hong Kong, Hong Kong, Peoples R China |
| 推荐引用方式 GB/T 7714 | Chen, S,Chang, SJ,Yuan, JH,et al. Adaptive training and pruning for neural networks: algorithms and application[J]. ACTA PHYSICA SINICA,2001,50:674-681. |
| APA | Chen, S,Chang, SJ,Yuan, JH,Zhang, YX,&Wong, KW.(2001).Adaptive training and pruning for neural networks: algorithms and application.ACTA PHYSICA SINICA,50,674-681. |
| MLA | Chen, S,et al."Adaptive training and pruning for neural networks: algorithms and application".ACTA PHYSICA SINICA 50(2001):674-681. |
入库方式： OAI收割
来源：近代物理研究所
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。