中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
A Novel Spatial Architecture Artificial Neural Network Based on Multilayer Feedforward Network with Mutual Inhibition among Hidden Units

文献类型:会议论文

作者Yang G(杨刚); Junfei Qiao; Yuan MZ(苑明哲)
出版日期2011
会议名称8th International Symposium on Neural Networks, ISNN 2011
会议日期May 29 - June 1, 2011
会议地点Guilin, China
关键词multilayer feedforward network spatial span connection lateral inhibition mechanism.
页码495-504
中文摘要We propose a Spatial Artificial Neural Network (SANN) with spatial architecture which consists of a multilayer feedforward neural network with hidden units adopt recurrent lateral inhibition connection, all input and hidden neurons have synapses connections with the output neurons. In addition, a supervised learning algorithm based on error back propagation is developed. The proposed network has shown a superior generalization capability in simulations with pattern recognition and non-linear function approximation problems. And, the experimental also shown that SANN has the capability of avoiding local minima problem.
收录类别EI ; CPCI(ISTP)
产权排序2
会议录Advances in Neural Networks - ISSN 2011. Proceedings of the 8th International Symposium on Neural Networks, ISNN 2011
会议录出版者Springer Verlag
会议录出版地Berlin, Germany
语种英语
ISBN号978-3-642-21104-1
WOS记录号WOS:000301802600057
源URL[http://ir.sia.cn/handle/173321/8311]  
专题沈阳自动化研究所_工业信息学研究室
推荐引用方式
GB/T 7714
Yang G,Junfei Qiao,Yuan MZ. A Novel Spatial Architecture Artificial Neural Network Based on Multilayer Feedforward Network with Mutual Inhibition among Hidden Units[C]. 见:8th International Symposium on Neural Networks, ISNN 2011. Guilin, China. May 29 - June 1, 2011.

入库方式: OAI收割

来源:沈阳自动化研究所

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。