Neural network interpretation using descrambler groups

The lack of interpretability and trust is a much-criticized feature of deep neural networks. In fully connected nets, the signaling between inner layers is scrambled because backpropagation training does not require perceptrons to be arranged in any particular order. The result is a black box; this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the National Academy of Sciences - PNAS 2021-02, Vol.118 (5), p.1-7
Hauptverfasser:	Amey, Jake L., Keeley, Jake, Choudhury, Tajwar, Kuprov, Ilya
Format:	Artikel
Sprache:	eng
Schlagworte:	Physical Sciences
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!