Credit assignment for trained neural networks based on Koopman operator theory

作     者：Zhen LIANG Changyuan ZHAO Wanwei LIU Bai XUE Wenjing YANG Zhengbin PANG Zhen LIANG;Changyuan ZHAO;Wanwei LIU;Bai XUE;Wenjing YANG;Zhengbin PANG

作者机构：Institute for Quantum Information&State Key Laboratory of High Performance ComputingNational University of Defense TechnologyChangsha 410000China Institute of SoftwareChinese Academy of SciencesBeijing 100190China College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410000China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2024年第18卷第1期

页      面：251-253页

核心收录：

学科分类：07[理学] 0835[工学-软件工程] 0701[理学-数学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 070101[理学-基础数学] 

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.61872371,61836005 and 62032024) the CAS Pioneer Hundred Talents Program 

主　　题：layer. assignment operator 

摘      要：1 Introduction Artificial neural networks(ANNs,also NNs)have recently emerged as leading candidate models for deep learning,popularly used in various areas[1–3].Behind the enormous success,ANNs are generally with complicated structures,there being an intricate data flow through multiple linear or nonlinear components between the input layer and the output ***,it is pressing to evaluate how much a specific component contributes to the final output,termed the Credit Assignment Problem(CAP)[4]in this paper.