A self-generating modular neural network architecture for supervised   learning

doi:10.1016/S0925-2312(96)00057-4

CORC > 北京大学 > 信息科学技术学院

	A self-generating modular neural network architecture for supervised learning
	Chen, K ; Yang, LP ; Yu, X ; Chi, HS
刊名	neurocomputing
	1997
关键词	modular neural networks self-generating architecture supervised learning TREES
DOI	10.1016/S0925-2312(96)00057-4
英文摘要	In this paper, we present a self-generating modular neural network architecture for supervised learning. In the architecture, any kind of feedforward neural networks can be employed as component nets. For a given task, a tree-structured modular neural network is automatically generated with a growing algorithm by partitioning input space recursively to avoid the problem of pre-determined structure. Due to the principle of divide-and-conquer used in the proposed architecture, the modular neural network can yield both good performance and significantly faster training. The proposed architecture has been applied to several supervised learning tasks and has achieved satisfactory results.; http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:A1997XJ02000003&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=8e1609b174ce4e31116a60747a720701 ; Computer Science, Artificial Intelligence; SCI(E); EI; 19; ARTICLE; 1; 33-48; 16
语种	英语
内容类型	期刊论文
源URL	[http://ir.pku.edu.cn/handle/20.500.11897/258285]
专题	信息科学技术学院
推荐引用方式 GB/T 7714	Chen, K,Yang, LP,Yu, X,et al. A self-generating modular neural network architecture for supervised learning[J]. neurocomputing,1997.
APA	Chen, K,Yang, LP,Yu, X,&Chi, HS.(1997).A self-generating modular neural network architecture for supervised learning.neurocomputing.
MLA	Chen, K,et al."A self-generating modular neural network architecture for supervised learning".neurocomputing (1997).