Credit assignment for trained neural networks based on Koopman operator theory
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.