Zeitschriftenartikel
Dealing with Mislabeling via Interactive Machine Learning
Vorschaubild nicht verfügbar
Volltext URI
Dokumententyp
Text/Journal Article
Zusatzinformation
Datum
2020
Autor:innen
Zeitschriftentitel
ISSN der Zeitschrift
Bandtitel
Verlag
Springer
Zusammenfassung
We propose an interactive machine learning framework where the machine questions the user feedback when it realizes it is inconsistent with the knowledge previously accumulated. The key idea is that the machine uses its available knowledge to check the correctness of its own and the user labeling. The proposed architecture and algorithms run through a series of modes with progressively higher confidence and features a conflict resolution component. The proposed solution is tested in a project on university student life where the goal is to recognize tasks like user location and transportation mode from sensor data. The results highlight the unexpected extreme pervasiveness of annotation mistakes and the advantages provided by skeptical learning.