TY - GEN
T1 - Deep learning regularization in imbalanced data
AU - Kamalov, Firuz
AU - Leung, Ho Hon
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/11/3
Y1 - 2020/11/3
N2 - Deep neural networks are known to have a large number of parameters which can lead to overfitting. As a result various regularization methods designed to mitigate the model overfitting have become an indispensable part of many neural network architectures. However, it remains unclear which regularization methods are the most effective. In this paper, we examine the impact of regularization on neural network performance in the context of imbalanced data. We consider three main regularization approaches: L{1}, L{2}, and dropout regularization. Numerical experiments reveal that the L{1} regularization method can be an effective tool to prevent overfitting in neural network models for imbalanced data. Index Terms-regularization, neural networks, imbalanced data.
AB - Deep neural networks are known to have a large number of parameters which can lead to overfitting. As a result various regularization methods designed to mitigate the model overfitting have become an indispensable part of many neural network architectures. However, it remains unclear which regularization methods are the most effective. In this paper, we examine the impact of regularization on neural network performance in the context of imbalanced data. We consider three main regularization approaches: L{1}, L{2}, and dropout regularization. Numerical experiments reveal that the L{1} regularization method can be an effective tool to prevent overfitting in neural network models for imbalanced data. Index Terms-regularization, neural networks, imbalanced data.
KW - imbalanced data
KW - neural networks
KW - regularization
UR - http://www.scopus.com/inward/record.url?scp=85097821573&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85097821573&partnerID=8YFLogxK
U2 - 10.1109/CCCI49893.2020.9256674
DO - 10.1109/CCCI49893.2020.9256674
M3 - Conference contribution
AN - SCOPUS:85097821573
T3 - Proceedings of the 2020 IEEE International Conference on Communications, Computing, Cybersecurity, and Informatics, CCCI 2020
BT - Proceedings of the 2020 IEEE International Conference on Communications, Computing, Cybersecurity, and Informatics, CCCI 2020
A2 - Obaidat, Mohammad S.
A2 - Hsiao, Kuei-Fang
A2 - Nicopolitidis, Petros
A2 - Guo, Yu
A2 - Cascado-Caballero, Daniel
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2020 IEEE International Conference on Communications, Computing, Cybersecurity, and Informatics, CCCI 2020
Y2 - 3 November 2020 through 5 November 2020
ER -