Double robustness analysis for determining optimal feedforward neural network architecture

CSpace > 系统科学研究所

	Double robustness analysis for determining optimal feedforward neural network architecture
	Yu, L ; Lai, KK ; Wang, SY
	2005
发表期刊	ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS
ISSN	0302-9743
卷号	3610 页码:382-385
摘要	This paper incorporates robustness into neural network modeling and proposes a novel two-phase robustness analysis approach for determining the optimal feedforward neural network (FNN) architecture in terms of Hellinger distance of probability density function (PDF) of error distribution. The proposed approach is illustrated with an example in this paper.
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods
WOS记录号	WOS:000232222400048
出版者	SPRINGER-VERLAG BERLIN
引用统计
文献类型	期刊论文
条目标识符	http://ir.amss.ac.cn/handle/2S8OKBNM/1093
专题	系统科学研究所
通讯作者	Yu, L
作者单位	1.Chinese Acad Sci, Acad Math & Syst Sci, Inst Syst Sci, Beijing 100080, Peoples R China 2.Hunan Univ, Coll Business Adm, Changsha 410082, Peoples R China 3.City Univ Hong Kong, Dept Management Sci, Kowloon, Hong Kong, Peoples R China
推荐引用方式 GB/T 7714	Yu, L,Lai, KK,Wang, SY. Double robustness analysis for determining optimal feedforward neural network architecture[J]. ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS,2005,3610:382-385.
APA	Yu, L,Lai, KK,&Wang, SY.(2005).Double robustness analysis for determining optimal feedforward neural network architecture.ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS,3610,382-385.
MLA	Yu, L,et al."Double robustness analysis for determining optimal feedforward neural network architecture".ADVANCES IN NATURAL COMPUTATION, PT 1, PROCEEDINGS 3610(2005):382-385.