Constructing the Basis Path Set by Eliminating the Path Dependency

作     者：ZHU Juanping MENG Qi CHEN Wei WANG Yue MA Zhiming ZHU Juanping;MENG Qi;CHEN Wei;WANG Yue;MA Zhiming

作者机构：School of Mathematics and StatisticsYunnan UniversityKunming 650500China Microsoft Research AsiaBeijing 100190China Academy of Mathematics and Systems ScienceChinese Academy of ScienceBeijing 100190China 

出 版 物：《Journal of Systems Science & Complexity》 (系统科学与复杂性学报（英文版）)

年 卷 期：2022年第35卷第5期

页      面：1944-1962页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by Project for Innovation Team(Cultivation)of Yunnan Province under Grant No.202005AE160006 Key Project of Yunnan Provincial Science and Technology Department and Yunnan University under Grant No.2018FY001014 

主　　题：Basis path neural network path dependency path subdivision chain substructure path 

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 *** the perspective of graph theory,the BasisP athSetSearching problem is formulated to find the basis path set in a complicated fully connected neural *** paper proposes algorithm DEAH to hierarchically solve the BasisP athSetSearching problem by eliminating the path *** this purpose,the authors discover the underlying cause of the path dependency between two independent *** path subdivision chain is proposed to effectively eliminate the path dependency,both inside the chain and between *** theoretical proofs and the analysis of time complexity are presented for Algorithm *** paper therefore provides one methodology to find the basis path set in a general and practical neural network.