AI & MLCoreAIML-GEN-010
Data Augmentation
Encoding invariances by transforming training examples: more effective data without more labels.
- Difficulty
- 2 / 5
- Importance
- 5 / 5
- Study time
- 1–2 h
- Kind of work
- Mixed
Why it matters
The learner can choose label-preserving augmentations for a task and predict their effect on the train/validation gap.