Phase 2 — Machine Learning Fundamentals
Weeks: 5–6 | Goal: Scikit-learn pipelines, data preprocessing, model evaluation metrics for CV
Labs
| Lab | Topic | Key Skills |
|---|---|---|
| lab-01-sklearn-pipeline | SVM, Random Forest, cross-validation | ML pipeline, hyperparameter search |
| lab-02-data-preprocessing | Normalization, augmentation, class imbalance | Albumentations, SMOTE, focal loss |
| lab-03-model-evaluation | Confusion matrix, mAP, ROC-AUC | Evaluation metrics for object detection |
Why ML Fundamentals Matter for CV Engineers
Many production CV systems use classical ML on top of CNN features:
- SVM on CNN embeddings (classic fine-grained recognition approach)
- One-class SVM for novelty detection / OOD detection
- Decision trees for interpretable defect classification in manufacturing
- k-NN in embedding space for zero-shot recognition
More importantly: evaluation metrics for CV are notoriously tricky. Misunderstanding mAP@0.5 vs mAP@0.5:0.95 in a model comparison is a senior-level interview red flag.