Deep Learning / 09
Regularization
Explore penalties, dropout, augmentation, and the tradeoffs in controlling model complexity.
This is a knowledge index. Published titles open their articles; the remaining entries outline planned coverage.
Subtopics
- 09.01
Why Regularization?
Planned guide: Why Regularization. Focus on intuition, assumptions, and a worked example.
- 09.02
L1 Regularization
Planned guide: L1 Regularization. Focus on intuition, assumptions, and a worked example.
- 09.03
L2 Regularization
Planned guide: L2 Regularization. Focus on intuition, assumptions, and a worked example.
- 09.04
Weight Decay
Planned guide: Weight Decay. Focus on intuition, assumptions, and a worked example.
- 09.05
Dropout
Planned guide: Dropout. Focus on intuition, assumptions, and a worked example.
- 09.06
DropConnect
Planned guide: DropConnect. Focus on intuition, assumptions, and a worked example.
- 09.07
Early Stopping
Planned guide: Early Stopping. Focus on intuition, assumptions, and a worked example.
- 09.08
Data Augmentation
Planned guide: Data Augmentation. Focus on intuition, assumptions, and a worked example.
- 09.09
Label Smoothing
Planned guide: Label Smoothing. Focus on intuition, assumptions, and a worked example.
- 09.10
Noise Injection
Planned guide: Noise Injection. Focus on intuition, assumptions, and a worked example.
- 09.11
Stochastic Depth
Planned guide: Stochastic Depth. Focus on intuition, assumptions, and a worked example.
- 09.12
Regularization Tradeoffs
Planned guide: Regularization Tradeoffs. Focus on intuition, assumptions, and a worked example.