Testing the Channels of Convolutional Neural Networks
- Title
- Testing the Channels of Convolutional Neural Networks
- Author
- 김영훈
- Keywords
- Machine Learning; Artificial Intelligence; Software Engineering
- Issue Date
- 2023-03-06
- Publisher
- AAAI Press
- Citation
- Association for the Advancement of Artificial Intelligence, 2023
- Abstract
- Neural networks have complex structures, and thus it is hard to understand their inner workings and ensure correctness. To understand and debug convolutional neural networks (CNNs) we propose techniques for testing the channels of CNNs. We design FtGAN, an extension to GAN, that can generate test data with varying the intensity (i.e., sum of the neurons) of a channel of a target CNN. We also proposed a channel selection algorithm to find representative channels for testing. To efficiently inspect the target CNN's inference computations, we define unexpectedness score, which estimates how similar the inference computation of the test data is to that of the training data. We evaluated FtGAN with five public datasets and showed that our techniques successfully identify defective channels in five different CNN models.
- URI
- https://information.hanyang.ac.kr/#/eds/detail?an=edsarx.2303.03400&dbId=edsarxhttps://repository.hanyang.ac.kr/handle/20.500.11754/189751
- ISSN
- 2769-1349; 2769-1330
- Appears in Collections:
- ETC[S] > 연구정보
- Files in This Item:
There are no files associated with this item.
- Export
- RIS (EndNote)
- XLS (Excel)
- XML