Number of the records: 1
Classification by ordinal sums of conjunctive and disjunctive functions for explainable AI and interpretable machine learning solutions
- 1.
SYSNO ASEP 0545167 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Classification by ordinal sums of conjunctive and disjunctive functions for explainable AI and interpretable machine learning solutions Author(s) Hudec, M. (SK)
Mináriková, E. (SK)
Mesiar, Radko (UTIA-B) RID, ORCID
Saranti, A. (AT)
Holzinger, A. (AT)Number of authors 5 Article number 106916 Source Title Knowledge-Based System. - : Elsevier - ISSN 0950-7051
Roč. 220, č. 1 (2021)Number of pages 12 s. Publication form Print - P Language eng - English Country NL - Netherlands Keywords Aggregation functions ; Explainable AI ; Interactive ML ; Interpretable Machine Learning (ML) ; Ordinal sums ; Glass-box ; Transparency Subject RIV BA - General Mathematics OECD category Applied mathematics Method of publishing Open access Institutional support UTIA-B - RVO:67985556 UT WOS 000637680300011 EID SCOPUS 85102149142 DOI 10.1016/j.knosys.2021.106916 Annotation We propose a novel classification according to aggregation functions of mixed behaviour by variability in ordinal sums of conjunctive and disjunctive functions. Consequently, domain experts are empowered to assign only the most important observations regarding the considered attributes. This has the advantage that the variability of the functions provides opportunities for machine learning to learn the best possible option from the data. Moreover, such a solution is comprehensible, reproducible and explainable-per-design to domain experts. In this paper, we discuss the proposed approach with examples and outline the research steps in interactive machine learning with a human-in-the-loop over aggregation functions. Although human experts are not always able to explain anything either, they are sometimes able to bring in experience, contextual understanding and implicit knowledge, which is desirable in certain machine learning tasks and can contribute to the robustness of algorithms. The obtained theoretical results in ordinal sums are discussed and illustrated on examples. Workplace Institute of Information Theory and Automation Contact Markéta Votavová, votavova@utia.cas.cz, Tel.: 266 052 201. Year of Publishing 2022 Electronic address https://www.sciencedirect.com/science/article/pii/S0950705121001799
Number of the records: 1