Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.25266 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911546103300096 |
|---|---|
| author | Zhang, Zhuofan Wiklicky, Herbert |
| author_facet | Zhang, Zhuofan Wiklicky, Herbert |
| contents | Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program when it is infeasible to test every single inputs. In this paper we apply the theory on neural networks for the same purpose: to analyse density distribution flow of all possible inputs of a neural network when a network has uncountably many or countable but infinitely many inputs. We show how this theoretical framework works in neural networks and then discuss different abstract domains and corresponding Moore-Penrose pseudo-inverses together with abstract transformers used in the framework. We also present experimental examples to show how this framework helps to analyse real world problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25266 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation Zhang, Zhuofan Wiklicky, Herbert Artificial Intelligence Probabilistic abstract interpretation is a theory used to extract particular properties of a computer program when it is infeasible to test every single inputs. In this paper we apply the theory on neural networks for the same purpose: to analyse density distribution flow of all possible inputs of a neural network when a network has uncountably many or countable but infinitely many inputs. We show how this theoretical framework works in neural networks and then discuss different abstract domains and corresponding Moore-Penrose pseudo-inverses together with abstract transformers used in the framework. We also present experimental examples to show how this framework helps to analyse real world problems. |
| title | Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.25266 |