Boundary thickness and robustness in learning models
–Neural Information Processing Systems
In this paper, we introduce the notion of the boundary thickness of a classifier, and we describe its connection with and usefulness for model robustness.
Neural Information Processing Systems
Oct-2-2025, 19:22:49 GMT
- Country:
- Asia > Middle East
- Jordan (0.04)
- North America
- Canada (0.04)
- United States > California
- Alameda County > Berkeley (0.14)
- Asia > Middle East
- Genre:
- Research Report > New Finding (0.46)
- Industry:
- Information Technology (1.00)
- Technology: