Back to Search
Start Over
SyReNN: A tool for analyzing deep neural networks.
- Source :
- International Journal on Software Tools for Technology Transfer; Apr2023, Vol. 25 Issue 2, p145-165, 21p
- Publication Year :
- 2023
-
Abstract
- Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. This paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN's decision boundaries, and repairing buggy DNNs. [ABSTRACT FROM AUTHOR]
- Subjects :
- ARTIFICIAL neural networks
Subjects
Details
- Language :
- English
- ISSN :
- 14332779
- Volume :
- 25
- Issue :
- 2
- Database :
- Complementary Index
- Journal :
- International Journal on Software Tools for Technology Transfer
- Publication Type :
- Academic Journal
- Accession number :
- 162700196
- Full Text :
- https://doi.org/10.1007/s10009-023-00695-1