Robust feature space separation for deep convolutional neural network training

Abstract This paper introduces two deep convolutional neural network training techniques that lead to more robust feature subspace separation in comparison to traditional training. Assume that dataset has M labels. The first method creates M deep convolutional neural networks called $$\{\text {DCNN}...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Ali Sekmen, Mustafa Parlaktuna, Ayad Abdul-Malek, Erdem Erdemir, Ahmet Bugra Koku
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	Springer 2021-11-01
Edice:	Discover Artificial Intelligence
Témata:	Deep Convolutional Neural Networks Subspace Separation Robust Deep Learning
On-line přístup:	https://doi.org/10.1007/s44163-021-00013-1
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!