Semantic Interpretation for Convolutional Neural Networks: What Makes a Cat a Cat?

Xu，Hao1; Chen，Yuntian2; Zhang，Dongxiao3,4

2022

10.1002/advs.202204723

Advanced Science   Impact Factor & Quartile

2198-3844

The interpretability of deep neural networks has attracted increasing attention in recent years, and several methods have been created to interpret the “black box” model. Fundamental limitations remain, however, that impede the pace of understanding the networks, especially the extraction of understandable semantic space. In this work, the framework of semantic explainable artificial intelligence (S-XAI) is introduced, which utilizes a sample compression method based on the distinctive row-centered principal component analysis (PCA) that is different from the conventional column-centered PCA to obtain common traits of samples from the convolutional neural network (CNN), and extracts understandable semantic spaces on the basis of discovered semantically sensitive neurons and visualization techniques. Statistical interpretation of the semantic space is also provided, and the concept of semantic probability is proposed. The experimental results demonstrate that S-XAI is effective in providing a semantic interpretation for the CNN, and offers broad usage, including trustworthiness assessment and semantic sample searching.

convolutional neural network interpretable machine learning semantic space trustworthiness assessment

English

Corresponding

2-s2.0-85139442228

Scopus

1.BIC-ESAT,ERE,and SKLTCS,College of Engineering,Peking University,Beijing,100871,China
2.Eastern Institute for Advanced Study,Yongriver Institute of Technology,Ningbo,Zhejiang,315200,China
3.National Center for Applied Mathematics Shenzhen (NCAMS),Southern University of Science and Technology,Shenzhen,Guangdong,518055,China
4.Department of Mathematics and Theories,Peng Cheng Laboratory,Shenzhen,Guangdong,518000,China

Xu，Hao,Chen，Yuntian,Zhang，Dongxiao. Semantic Interpretation for Convolutional Neural Networks: What Makes a Cat a Cat?[J]. Advanced Science,2022.

Xu，Hao,Chen，Yuntian,&Zhang，Dongxiao.(2022).Semantic Interpretation for Convolutional Neural Networks: What Makes a Cat a Cat?.Advanced Science.

Xu，Hao,et al."Semantic Interpretation for Convolutional Neural Networks: What Makes a Cat a Cat?".Advanced Science (2022).