machine-learning
Features, samples, and training/validation/test splits
taught
The formal vocabulary for a dataset's parts, and why a model is evaluated on data it never trained on.
Taught in
-
Features, samples, and data splits
Modern Machine Learning
Requires
- data-as-vectors-and-matrices required
Required by
- Data leakage, spotted during EDA required
- Generalization required
- The validation-set approach and its weaknesses 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.