Lessons on interpretable machine learning from particle physics

Machine learning methods have proved powerful in particle physics, but without interpretability there is no guarantee the outcome of a learning algorithm is correct or robust. Christophe Grojean, Ayan Paul, Zhuoni Qian and Inga Strümke give an overview of how to introduce interpretability to methods...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Nature reviews physics Jg. 4; H. 5; S. 284 - 286
Hauptverfasser: Grojean, Christophe, Paul, Ayan, Qian, Zhuoni, Strümke, Inga
Format: Journal Article
Sprache:Englisch
Veröffentlicht: London Nature Publishing Group 01.05.2022
Schlagworte:
Algorithms
Artificial intelligence
Decision trees
Kinematics
Machine learning
Neural networks
Particle physics
Variables
ISSN:2522-5820
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Machine learning methods have proved powerful in particle physics, but without interpretability there is no guarantee the outcome of a learning algorithm is correct or robust. Christophe Grojean, Ayan Paul, Zhuoni Qian and Inga Strümke give an overview of how to introduce interpretability to methods commonly used in particle physics.
Bibliographie:SourceType-Scholarly Journals-1
ObjectType-Commentary-1
content type line 14
ISSN:2522-5820
DOI:10.1038/s42254-022-00456-0