| Autor: |
Boumazouza, Ryma, Cheikh-Alili, Fahima, Mazure, Bertrand, Tabia, Karim |
| Rok vydání: |
2022 |
| Předmět: |
|
| Zdroj: |
The 23rd International Conference on Artificial Intelligence (ICAI'21), Jul 2021, Las Vegas, United States. https://www.springer.com/series/11769 |
| Druh dokumentu: |
Working Paper |
| Popis: |
In this paper titled A Model-Agnostic SAT-based approach for Symbolic Explanation Enumeration we propose a generic agnostic approach allowing to generate different and complementary types of symbolic explanations. More precisely, we generate explanations to locally explain a single prediction by analyzing the relationship between the features and the output. Our approach uses a propositional encoding of the predictive model and a SAT-based setting to generate two types of symbolic explanations which are Sufficient Reasons and Counterfactuals. The experimental results on image classification task show the feasibility of the proposed approach and its effectiveness in providing Sufficient Reasons and Counterfactuals explanations. |
| Databáze: |
arXiv |
| Externí odkaz: |
|
