典型文献
Constructing the Basis Path Set by Eliminating the Path Dependency
文献摘要：
The newly appeared g-SGD algorithm can only heuristically find the basis path set in a simple neural network,so its generalization to a more practical network is hindered.From the perspective of graph theory,the BasisPathSetSearching problem is formulated to find the basis path set in a complicated fully connected neural network.This paper proposes algorithm DEAH to hierarchically solve the BasisPathSetSearching problem by eliminating the path dependencies.For this purpose,the authors discover the underlying cause of the path dependency between two independent substructures.The path subdivision chain is proposed to effectively eliminate the path dependency,both inside the chain and between chains.The theoretical proofs and the analysis of time complexity are presented for Algorithm DEAH.This paper therefore provides one methodology to find the basis path set in a general and practical neural network.
文献关键词：
中图分类号：
作者姓名：
ZHU Juanping;MENG Qi;CHEN Wei;WANG Yue;MA Zhiming
作者机构：
School of Mathematics and Statistics,Yunnan University,Kunming 650500,China;Microsoft Research Asia,Beijing 100190,China;Academy of Mathematics and Systems Science,Chinese Academy of Science,Beijing 100190,China
文献出处：
引用格式：
[1]ZHU Juanping;MENG Qi;CHEN Wei;WANG Yue;MA Zhiming-.Constructing the Basis Path Set by Eliminating the Path Dependency)[J].系统科学与复杂性学报（英文版）,2022(05):1944-1962
A类：
BasisPathSetSearching
B类：
Constructing,by,Eliminating,Dependency,newly,appeared,SGD,algorithm,can,only,heuristically,find,basis,path,set,simple,neural,network,its,generalization,more,practical,hindered,From,perspective,graph,theory,problem,formulated,complicated,fully,connected,This,paper,proposes,DEAH,hierarchically,solve,eliminating,dependencies,For,this,purpose,authors,discover,underlying,cause,dependency,between,independent,substructures,subdivision,proposed,effectively,eliminate,both,inside,chains,theoretical,proofs,analysis,complexity,presented,Algorithm,therefore,provides,one,methodology
AB值：
0.562982
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
