Convolutional neural networks with dynamic regularization
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...
Saved in:
Main Authors: | Wang, Yi, Bian, Zhen-Peng, Hou, Junhui, Chau, Lap-Pui |
---|---|
Other Authors: | School of Electrical and Electronic Engineering |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/159626 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
An energy-efficient convolution unit for depthwise separable convolutional neural networks
by: Chong, Yi Sheng, et al.
Published: (2021) -
Hardware-friendly stochastic and adaptive learning in memristor convolutional neural networks
by: Zhang, Wei, et al.
Published: (2022) -
Light field denoising via anisotropic parallax analysis in a CNN framework
by: Chen, Jie, et al.
Published: (2020) -
A convolutional neural network-based auto-segmentation pipeline for breast cancer imaging
by: Leow, Lucas Jian Hoong, et al.
Published: (2024) -
Ultra-high-speed accelerator architecture for convolutional neural network based on processing-in-memory using resistive random access memory
by: Wang, Hongzhe, et al.
Published: (2023)