Szczegóły publikacji
Opis bibliograficzny
Introducing uncertainty into explainable AI methods / Szymon Bobek, Grzegorz J. Nalepa // W: Computational Science – ICCS 2021 : 21st International Conference : Krakow, Poland, June 16–18, 2021 : proceedings, Pt. 6 / eds. Maciej Paszyński, [et al.]. — Cham : Springer Nature Switzerland, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12747. Theoretical Computer Science and General Issues ; ISSN 0302-9743). — ISBN: 978-3-030-77979-5; e-ISBN: 978-3-030-77980-1. — S. 444–457. — Bibliogr., Abstr. — Publikacja dostępna online od: 2021-06-09. — Sz. Bobek, G. J. Nalepa - afiliacja: Jagiellonian Human-Centered Artificial Intelligence Laboratory (JAHCAI) and Institute of Applied Computer Science, Jagiellonian University
Autorzy (2)
- Bobek Szymon
- Nalepa Grzegorz Jacek
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 134765 |
|---|---|
| Data dodania do BaDAP | 2021-06-28 |
| DOI | 10.1007/978-3-030-77980-1_34 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Computational Science 2021 |
| Czasopisma/serie | Lecture Notes in Computer Science, Theoretical Computer Science and General Issues |
Abstract
Learning from uncertain or incomplete data is one of the major challenges in building artificial intelligence systems. However, the research in this area is more focused on the impact of uncertainty on the algorithms performance or robustness, rather than on human understanding of the model and the explainability of the system. In this paper we present our work in the field of knowledge discovery from uncertain data and show its potential usage for the purpose of improving system interpretability by generating Local Uncertain Explanations (LUX) for machine learning models. We present a method that allows to propagate uncertainty of data into the explanation model, providing more insight into the certainty of the decision making process and certainty of explanations of these decisions. We demonstrate the method on synthetic, reproducible dataset and compare it to the most popular explanation frameworks.
