期刊
SOFT COMPUTING
卷 26, 期 14, 页码 6519-6527出版社
SPRINGER
DOI: 10.1007/s00500-022-07128-2
关键词
Fuzziness; Strong fuzzy partition; Fuzzy rule-based classifier; XAI
资金
- Universita degli Studi di Bari Aldo Moro within the CRUI-CARE Agreement
- Ministero dell'Istruzione, dell'Universita e della Ricerca (MIUR) [PON ARS01_00141]
Fuzziness has an impact on the behavior of Fuzzy Rule-Based Classifiers, but only in regions where the classification confidence is low. Therefore, in Explainable Artificial Intelligence, fuzziness is beneficial in FRBCs only when accompanied by an explanation of the output confidence.
We study the impact of fuzziness on the behavior of Fuzzy Rule-Based Classifiers (FRBCs) defined by trapezoidal fuzzy sets forming Strong Fuzzy Partitions. In particular, if an FRBC selects the class related to the rule with the highest activation (so-called Winner-Takes-All approach), then fuzziness, as quantified by the slope of the membership functions, has no impact in classifying data in regions of the input space where rules dominate. On the other hand, fuzziness affects the behaviour of the FRBC in regions where the confidence in classification is low. As a consequence, in the context of Explainable Artificial Intelligence, fuzziness is profitable in FRBCs only if classification is accompanied by an explanation of the confidence of the provided outputs.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据