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}...
Guardado en:
Autores principales: | Ali Sekmen, Mustafa Parlaktuna, Ayad Abdul-Malek, Erdem Erdemir, Ahmet Bugra Koku |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
Springer
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/0c4975ea7511433cbff1e6d106499b8e |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
EVALITA4ELG: Italian Benchmark Linguistic Resources, NLP Services and Tools for the ELG Platform
por: Viviana Patti, et al.
Publicado: (2020) -
On the Readability of Kernel-based Deep Learning Models in Semantic Role Labeling Tasks over Multiple Languages
por: Daniele Rossini, et al.
Publicado: (2019) -
Introduction to the Special Issue on Digital Humanities and Computational Linguistics
por: John Nerbonne, et al.
Publicado: (2016) -
Lost in Text: A Cross-Genre Analysis of Linguistic Phenomena within Text
por: Chiara Buongiovanni, et al.
Publicado: (2020) -
CLARIN, l’infrastruttura europea delle risorse linguistiche per le scienze umane e sociali e il suo network italiano CLARIN-IT
por: Monica Monachini, et al.
Publicado: (2016)