Artykuł w czasopiśmie
Brak miniatury
Licencja
Dostęp zamkniętyBrightBox — A rough set based technology for diagnosing mistakes of machine learning models
| cris.lastimport.scopus | 2024-02-12T19:40:18Z |
| dc.abstract.en | The paper presents a novel approach to investigating mistakes in machine learning model operations. The considered approach is the basis for BrightBox – a diagnostic technology that can be used for analyzing prediction models and identifying model- and data-related issues. The idea is to generate surrogate rough set-based models from data that approximate decisions made by monitored black-box models. Such approximators are used to compute neighborhoods of instances that undergo the diagnostic process — the neighborhoods consist of historical instances that were processed in a similar way by rough set-based models. The diagnostic process is then based on the analysis of mistakes registered in such neighborhoods. The experiments performed on real-world data sets confirm that such analysis can provide us with efficient and valid insights about the reasons for the poor performance of machine learning models. |
| dc.affiliation | Uniwersytet Warszawski |
| dc.contributor.author | Ślęzak, Dominik |
| dc.contributor.author | Sikora, Marek |
| dc.contributor.author | Ludziejewski, Jan |
| dc.contributor.author | Biczyk, Piotr |
| dc.contributor.author | Wawrowski, Łukasz |
| dc.contributor.author | Zalewska, Andżelika |
| dc.contributor.author | Janusz, Andrzej |
| dc.date.accessioned | 2024-01-24T18:55:17Z |
| dc.date.available | 2024-01-24T18:55:17Z |
| dc.date.issued | 2023 |
| dc.description.finance | Publikacja bezkosztowa |
| dc.description.volume | 141 |
| dc.identifier.doi | 10.1016/J.ASOC.2023.110285 |
| dc.identifier.issn | 1568-4946 |
| dc.identifier.uri | https://repozytorium.uw.edu.pl//handle/item/102543 |
| dc.identifier.weblink | https://api.elsevier.com/content/article/PII:S1568494623003034?httpAccept=text/xml |
| dc.language | eng |
| dc.pbn.affiliation | computer and information sciences |
| dc.relation.ispartof | Applied Soft Computing Journal |
| dc.relation.pages | 110285, 1-14 |
| dc.rights | ClosedAccess |
| dc.sciencecloud | nosend |
| dc.subject.en | Machine learning diagnostics |
| dc.subject.en | Surrogate models |
| dc.subject.en | Model approximation |
| dc.subject.en | Rough sets |
| dc.subject.en | Ensembles of reducts |
| dc.subject.en | Explainable artificial intelligence |
| dc.subject.en | BrightBox technology |
| dc.title | BrightBox — A rough set based technology for diagnosing mistakes of machine learning models |
| dc.type | JournalArticle |
| dspace.entity.type | Publication |