Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.25273 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915892522123264 |
|---|---|
| author | Zhang, Zhuofan Wiklicky, Herbert |
| author_facet | Zhang, Zhuofan Wiklicky, Herbert |
| contents | The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by analyzing its density distribution flow of all possible inputs. The grids approximation is one of abstract domains the framework uses which abstracts concrete space into grids. In this paper, we introduce two novel approximation methods: distribution approximation and clusters approximation. We show how these two methods work in theory with corresponding abstract transformers with help of illustrations of some simple examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25273 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis Zhang, Zhuofan Wiklicky, Herbert Artificial Intelligence The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by analyzing its density distribution flow of all possible inputs. The grids approximation is one of abstract domains the framework uses which abstracts concrete space into grids. In this paper, we introduce two novel approximation methods: distribution approximation and clusters approximation. We show how these two methods work in theory with corresponding abstract transformers with help of illustrations of some simple examples. |
| title | Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.25273 |