Convolutional neural networks with dynamic regularization

• Main Authors: Wang, Yi, Bian, Zhen-Peng, Hou, Junhui, Chau, Lap-Pui
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Article
• 語言: English
• 出版: 2022
• 主題: Engineering::Electrical and electronic engineering; Convolutional Neural Network; Generalization
• 在線閱讀: https://hdl.handle.net/10356/159626
• 機構: Nanyang Technological University

Regularization is commonly used for alleviating overfitting in machine learning. For convolutional neural networks (CNNs), regularization methods, such as DropBlock and Shake-Shake, have illustrated the improvement in the generalization performance. However, these methods lack a self-adaptive abilit...