Feature Learning With a Divergence-Encouraging Autoencoder for Imbalanced Data Classification

Feature Learning With a Divergence-Encouraging Autoencoder for Imbalanced Data Classification

Imbalanced data exists commonly in machine learning classification applications. Popular classification algorithms are based on the assumption that data in different classes are roughly equally distributed; however, extremely skewed data, with instances from one class taking up most of the dataset,...

Full description

Bibliographic Details
Main Authors: Ruisen Luo, Qian Feng, Chen Wang, Xiaomei Yang, Haiyan Tu, Qin Yu, Shaomin Fei, Xiaofeng Gong
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Imbalanced data classification
autoencoder
divergence loss
convergence analysis
alternating training paradigm
Online Access:https://ieeexplore.ieee.org/document/8519727/

Internet

https://ieeexplore.ieee.org/document/8519727/

Similar Items