期刊文献+
共找到1篇文章
< 1 >
每页显示 20 50 100
Credit assignment for trained neural networks based on Koopman operator theory
1
作者 Zhen LIANG changyuan zhao +3 位作者 Wanwei LIU Bai XUE Wenjing YANG Zhengbin PANG 《Frontiers of Computer Science》 SCIE EI CSCD 2024年第1期251-253,共3页
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 com... 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 layer.Consequently,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. 展开更多
关键词 layer. ASSIGNMENT OPERATOR
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部