卷积神经网络的可解释性研究综述

Translated title of the contribution: Survey on Convolutional Neural Network Interpretability

Hui Dou, Ling Ming Zhang, Feng Han, Fu Rao Shen, Jian Zhao

Research output: Contribution to journalArticlepeer-review

Abstract

With the increasingly powerful performance of neural network models, they are widely used to solve various computer-related tasks and show excellent capabilities. However, a clear understanding of the operation mechanism of neural network models is lacking. Therefore, this study reviews and summarizes the current research on the interpretability of neural networks. A detailed discussion is rendered on the definition, necessity, classification, and evaluation of research on model interpretability. With the emphasis on the focus of interpretable algorithms, a new classification method for the interpretable algorithms of neural networks is proposed, which provides a novel perspective for the understanding of neural networks. According to the proposed method, this study sorts out the current interpretable methods for convolutional neural networks and comparatively analyzes the characteristics of interpretable algorithms falling within different categories. Moreover, it introduces the evaluation principles and methods of common interpretable algorithms and expounds on the research directions and applications of interpretable neural networks. Finally, the problems confronted in this regard are discussed, and possible solutions to these problems are given.

Translated title of the contributionSurvey on Convolutional Neural Network Interpretability
Original languageChinese (Traditional)
Pages (from-to)159-184
Number of pages26
JournalRuan Jian Xue Bao/Journal of Software
Volume35
Issue number1
DOIs
StatePublished - Jan 2024
Externally publishedYes

Keywords

  • deep learning
  • interpretability
  • neural network
  • taxonomy

ASJC Scopus subject areas

  • Software

Fingerprint

Dive into the research topics of 'Survey on Convolutional Neural Network Interpretability'. Together they form a unique fingerprint.

Cite this