Wird geladen...

Maximum Relevance Minimum Redundancy Dropout with Informative Kernel Determinantal Point Process

In recent years, deep neural networks have shown significant progress in computer vision due to their large generalization capacity; however, the overfitting problem ubiquitously threatens the learning process of these highly nonlinear architectures. Dropout is a recent solution to mitigate overfitt...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Sensors (Basel)
Hauptverfasser: Saffari, Mohsen, Khodayar, Mahdi, Ebrahimi Saadabadi, Mohammad Saeed, Sequeira, Ana F., Cardoso, Jaime S.
Format: Artigo
Sprache:Inglês
Veröffentlicht: MDPI 2021
Schlagworte:
Online Zugang:https://ncbi.nlm.nih.gov/pmc/articles/PMC7961777/
https://ncbi.nlm.nih.gov/pubmed/33800810
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.3390/s21051846
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!