A comparative study of two modeling approaches in neural networks
文献类型：期刊论文
| 作者 | Xu, ZB ; Qiao, H; Peng, JG; Zhang, B
|
| 刊名 | NEURAL NETWORKS
 |
| 出版日期 | 2004-01 |
| 卷号 | 17期号:1页码:73-85 |
| 关键词 | static neural network modeling local field neural network modeling recurrent neural networks stability analysis asymptotic stability exponential stability global convergence globally attractive |
| 通讯作者 | Xu, ZB |
| 中文摘要 | |
| 英文摘要 | The neuron state modeling and the local field modeling provides two fundamental modeling approaches to neural network research, based on which a neural network system can be called either as a static neural network model or as a local field neural network model. These two models are theoretically compared in terms of their trajectory, transformation property, equilibrium correspondence property, nontrivial attractive manifold property, global convergence as well as stability in many different senses. The comparison reveals an important stability invariance property of the two models in the sense that the stability (in any sense) of the static model is equivalent to that of a subsystem deduced from the local field model when restricted to a specific manifold. Such stability invariance property lays a sound theoretical foundation of validity of a useful, cross-fertilization type stability analysis methodology for various neural network models. (C) 2003 Elsevier Ltd. All rights reserved. |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12573]  |
| 专题 | 自动化研究所_09年以前成果 |
| 作者单位 | Coventry Univ, Sch Math & Informat Sci |
| 推荐引用方式 GB/T 7714 | Xu, ZB,Qiao, H,Peng, JG,et al. A comparative study of two modeling approaches in neural networks[J]. NEURAL NETWORKS,2004,17(1):73-85. |
| APA | Xu, ZB,Qiao, H,Peng, JG,&Zhang, B.(2004).A comparative study of two modeling approaches in neural networks.NEURAL NETWORKS,17(1),73-85. |
| MLA | Xu, ZB,et al."A comparative study of two modeling approaches in neural networks".NEURAL NETWORKS 17.1(2004):73-85. |
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。