浏览全部资源
扫码关注微信
[ "赵晋明(1973-),男,山西省太原市文通电子有限公司研发主管,主要研究方向为网络管理系统的架构和关键算法,具有丰富的理论和工程经验,为中国移动通信集团等运营商解决了大量运维难题,并实现多项关键技术突破。" ]
网络出版日期:2016-08,
纸质出版日期:2016-08-20
移动端阅览
赵晋明. 一种基于随机映射的网络状态评估方法[J]. 电信科学, 2016,32(8):164-168.
Jinming ZHAO. A network status evaluation method based on random projection[J]. Telecommunications science, 2016, 32(8): 164-168.
赵晋明. 一种基于随机映射的网络状态评估方法[J]. 电信科学, 2016,32(8):164-168. DOI: 10.11959/j.issn.1000-0801.2016224.
Jinming ZHAO. A network status evaluation method based on random projection[J]. Telecommunications science, 2016, 32(8): 164-168. DOI: 10.11959/j.issn.1000-0801.2016224.
近年来,机器学习技术在网络管理领域得到了广泛使用。然而由于通信网络日益复杂,网络中的非线性和不确定因素使得机器学习变得十分困难。为了提升机器学习的效果,提出了一种采用随机映射的人工神经网络方案,其特点是引入机器学习和网络拓扑的随机性,使得神经网络对学习目标具有更大的适应性,并实现更快、更精确的收敛。相关成果已经在中国移动通信集团山西有限公司(以下简称山西移动)的实际网络中得到了应用并取得较好的效果。
In recent years,machine learning has been widely used in network management.However,the complexity of the communication network is increasing,nonlinear and uncertain factors in the network make the machine learning more difficult.In order to improve the effect of machine learning,a scheme of artificial nervous network based on random projection was proposed.The characteristic of such scheme was the introduction of randomness in machine learning and network topology,which took the learning process more adaptability,and achieve faster and more accurate convergence.
KARUNASINGHE D , LIONG S Y . Chaotic prediction with global model artificial neural network [J ] . Journal of Hydrology , 2006 , 323 ( 1 ): 92 - 105 .
黎明 , 张化光 . 神经网络建模方法研究 [J ] . 自动化学报 , 2002 , 28 ( 1 ): 27 - 33 .
LI M , ZHANG H G . Research of neural network modelling method [J ] . Acta Automatica Sinica , 2002 , 28 ( 1 ): 27 - 33 .
YU H , REINER P D , XIE T , et al . An incremental design of radial basis function network [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2014 , 25 ( 10 ): 1793 - 1083 .
MALL R , SUYKENS J A K . Very sparse LSSVM reductions for large-scale data [J ] . IEEE Transactions on Neural Networks and Learning Systems , 2015 , 26 ( 5 ): 1086 - 1097 .
PEARLMUTTER B A . Gradient calculations for dynamic recurrent neural networks:a survey [J ] . IEEE Transactions on Neural Networks , 1995 , 6 ( 5 ): 1212 - 1228 .
ATIYA A F , PARLOS A G . New results on recurrent network training:unifying the algorithms and accelerating convergence [J ] . IEEE Transactions on Neural Networks , 2000 , 11 ( 3 ): 697 - 709 .
ARRIAGA R I , RUTTER D , CAKMAK M , et al . Visual categorization with random projection [J ] . Neural Computation , 2015 , 27 ( 10 ): 2132 - 2143 .
PAO Y H , TAKEFVJI Y . Functional-link net computing [J ] . IEEE Computer Journal , 1992 , 25 ( 5 ): 76 - 79 .
0
浏览量
891
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构