Paper
2 May 2023 Research on the interpretability of neural networks applied in image classification
Binglin Liu, Haitian Liu, Junchao Du, Qianchao Hu, Feng Wang
Author Affiliations +
Proceedings Volume 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023); 126422E (2023) https://doi.org/10.1117/12.2674745
Event: Second International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT 2023), 2023, Xishuangbanna, China
Abstract
Artificial intelligence technology is a strategic technology leading a new era of the revolution of science and technology along with the industry transformation. However, with the progress of technology and the boosting complexity of model, the problem of lacking of interpretability of artificial intelligence has become extremely acute. From theoretical research to practical application, the obstacle caused by its poor interpretability has become a major weakness of AI at present. This paper proposes to evaluate the interpretability via robustness and induced metrics. And then, this paper gives some existing image-classification networks a comparison and an evaluation of robustness and interpretability, and get the interpretation of models shown in heatmap.
© (2023) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Binglin Liu, Haitian Liu, Junchao Du, Qianchao Hu, and Feng Wang "Research on the interpretability of neural networks applied in image classification", Proc. SPIE 12642, Second International Conference on Electronic Information Engineering, Big Data, and Computer Technology (EIBDCT 2023), 126422E (2 May 2023); https://doi.org/10.1117/12.2674745
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Neural networks

Neurons

Artificial intelligence

Deep learning

Image classification

Systems modeling

Machine learning

Back to Top