Difference between revisions of "Early Stopping"
m |
|||
| Line 13: | Line 13: | ||
* add more data | * add more data | ||
| − | * use [[Data Augmentation]] | + | * use [[Data Augmentation, Data Labeling, and Auto-Tagging|Data Augmentation]] |
* use [[Batch Norm(alization) & Standardization]] | * use [[Batch Norm(alization) & Standardization]] | ||
* use architectures that generalize well | * use architectures that generalize well | ||
Revision as of 00:01, 19 September 2020
Youtube search... ...Google search
Good practices for addressing the Overfitting Challenge:
- add more data
- use Data Augmentation
- use Batch Norm(alization) & Standardization
- use architectures that generalize well
- reduce architecture complexity
- add Regularization
- L1 and L2 Regularization - update the general cost function by adding another term known as the regularization term.
- Dropout - at every iteration, it randomly selects some nodes and temporarily removes the nodes (along with all of their incoming and outgoing connections)
- Data Augmentation
- Early Stopping
