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

Abstract: 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.

Location
Deutsche Nationalbibliothek Frankfurt am Main
Extent
Online-Ressource
Language
Englisch

Bibliographic citation
Semantic Interpretation for Convolutional Neural Networks: What Makes a Cat a Cat? ; day:10 ; month:10 ; year:2022 ; extent:14
Advanced science ; (10.10.2022) (gesamt 14)

Creator
Xu, Hao
Chen, Yuntian
Zhang, Dongxiao

DOI
10.1002/advs.202204723
URN
urn:nbn:de:101:1-2022101115183303937096
Rights
Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
Last update
15.08.2025, 7:39 AM CEST

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.

Associated

Other Objects (12)