Re-Calibrating Network by Refining Initial Features Through Generative Gradient Regularization
In the domain of Deep Neural Networks (DNNs), the deployment of regularization techniques is a common strategy for optimizing network performance. While these methods have been shown to be effective for optimization, they typically necessitate complete retraining of the network. We propose a trainin...
Saved in:
| Main Authors: | Naim Reza, Ho Yub Jung |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10854681/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
GENERALIZATION OF VON-NEUMANN REGULAR RINGS TO VON-NEUMANN REGULAR MODULES
by: Hubbi Muhammad, et al.
Published: (2023-12-01) -
SOME RESULTS ON STRONGLY π-REGULAR RIN
by: Sinan O. Al-Salihi, et al.
Published: (2023-04-01) -
A strain based Lipschitz regularization for materials undergoing damage
by: Kamasamudram, Vasudevan, et al.
Published: (2023-03-01) -
4-REGULAR GRAPH OF DIAMETER 2
by: Đỗ Như An, et al.
Published: (2013-06-01) -
On regular spherical fuzzy graph
by: B. Mohamed Harif, et al.
Published: (2023-12-01)