The shallowest transparent and interpretable deep neural network for image recognition

Abstract Trusting the decisions of deep learning models requires transparency of their reasoning process, especially for high-risk decisions. In this paper, a fully transparent deep learning model (Shallow-ProtoPNet) is introduced. This model consists of a transparent prototype layer, followed by an...

Πλήρης περιγραφή

Λεπτομέρειες βιβλιογραφικής εγγραφής

Κύριοι συγγραφείς:	Gurmail Singh, Stefano Frizzo Stefenon, Kin-Choong Yow
Μορφή:	Artigo
Γλώσσα:	Inglês
Έκδοση:	Nature Portfolio 2025-04-01
Σειρά:	Scientific Reports
Θέματα:	Deep learning Image classification Interpretable models Prototypical part network
Διαθέσιμο Online:	https://doi.org/10.1038/s41598-025-92945-2
Ετικέτες:	Προσθήκη ετικέτας Δεν υπάρχουν, Καταχωρήστε ετικέτα πρώτοι!