- Tytuł:
- Towards explainable classifiers using the counterfactual approach : global explanations for discovering bias in data
- Autorzy:
-
Mikołajczyk, Agnieszka
Grochowski, Michał
Kwasigroch, Arkadiusz - Powiązania:
- https://bibliotekanauki.pl/articles/2031144.pdf
- Data publikacji:
- 2021
- Wydawca:
- Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
- Tematy:
-
explainable classifiers
counterfactual approach
bias detection - Opis:
- The paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results are validated on a sample skin lesion dataset. Using the proposed method, a number of possible bias-causing artifacts are successfully identified and confirmed in dermoscopy images. In particular, it is confirmed that black frames have a strong influence on Convolutional Neural Network’s prediction: 22% of them changed the prediction from benign to malignant.
- Źródło:
-
Journal of Artificial Intelligence and Soft Computing Research; 2021, 11, 1; 51-67
2083-2567
2449-6499 - Pojawia się w:
- Journal of Artificial Intelligence and Soft Computing Research
- Dostawca treści:
- Biblioteka Nauki
Artykuł