A copula-based visualization technique for a neural network

Interpretability of machine learning is defined as the extent to which humans can comprehend the reason of a decision. However, a neural network is not considered interpretable due to the ambiguity in its decision-making process. Therefore, in this study, we propose a new algorithm that reveals whic...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2020-03
Hauptverfasser:	Kubo, Yusuke, Komori, Yuto, Okuyama, Toyonobu, Tokieda, Hiroshi
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Correlation coefficients Decision making Decision trees Machine learning Mathematical analysis Neural networks Parameter identification
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!