deep-learning
Overfitting and underfitting
taught
Taught in
-
Memorizing versus learning: overfitting and underfitting
Deep Learning / Neural Networks
Requires
- train-validation-test-split required
Required by
- Data augmentation required
- Diagnosing a network that isn't learning required
- Distribution shift and dataset bias required
- Dropout required
- The bias-variance tradeoff required
- Weight decay required
Local knowledge map
Local knowledge map
Click to expand
Solid arrows are required prerequisites; dashed are recommended or helpful. Lower rows are more foundational. Click any box to jump to that concept.