Robust feature space separation for deep convolutional neural network training

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}...

Full description

Bibliographic Details
Main Authors: Ali Sekmen, Mustafa Parlaktuna, Ayad Abdul-Malek, Erdem Erdemir, Ahmet Bugra Koku
Format: Article
Language:English
Published: Springer 2021-11-01
Series:Discover Artificial Intelligence
Subjects:
Deep Convolutional Neural Networks
Subspace Separation
Robust Deep Learning
Online Access:https://doi.org/10.1007/s44163-021-00013-1

Internet

https://doi.org/10.1007/s44163-021-00013-1

Similar Items