Difference between revisions of "Early Stopping"
| Line 1: | Line 1: | ||
[http://www.youtube.com/results?search_query=Early+Stopping+Regularization+Dropout+Overfitting Youtube search...] | [http://www.youtube.com/results?search_query=Early+Stopping+Regularization+Dropout+Overfitting Youtube search...] | ||
[http://www.google.com/search?q=Early+Stopping+Regularization+Dropout+deep+machine+learning+ML ...Google search] | [http://www.google.com/search?q=Early+Stopping+Regularization+Dropout+deep+machine+learning+ML ...Google search] | ||
| + | |||
| + | * [http://en.wikipedia.org/wiki/Early_stopping Early Stopping | Wikipedia] | ||
Revision as of 16:28, 30 December 2018
Youtube search... ...Google search
Good practices for addressing overfitting:
- add more data
- use Data Augmentation
- use batch normalization
- 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
