Active Learning of Pattern Classification Based on PEDCC-Loss
Deep learning classifiers require a large number of labeled samples to train the model. Active learning reduces the dependence of classification model on labeled samples by gradually selecting high-quality samples for iterative training. In this article, an active learning method for pattern classif...
Guardado en:
Autores principales: | Qiuyu Zhu, Jianbing Luan, Tiantian Li, Xuewen Zu |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
IEEE
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/79ec406f64c141e78db6def879c1bb4b |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
Ejemplares similares
-
A Method for MBTI Classification Based on Impact of Class Components
por: Ninoslav Cerkez, et al.
Publicado: (2021) -
AE-MLP: A Hybrid Deep Learning Approach for DDoS Detection and Classification
por: Yuanyuan Wei, et al.
Publicado: (2021) -
A Learning Objective Controllable Sphere-Based Method for Balanced and Imbalanced Data Classification
por: Yeontark Park, et al.
Publicado: (2021) -
Symmetric mean and directional contour pattern for texture classification
por: Yongsheng Dong, et al.
Publicado: (2021) -
INVESTIGATION OF LOSSES IN INSULATION OF HIGH-VOLTAGE CABLES WITH XLPE INSULATION
por: L.A. Shchebeniuk, et al.
Publicado: (2016)