Interactive session, Thursday March 17
Weekly lecture:
Slides
Video Recordings:
- Overview
- scikit-learn applied to the 2021 mandatory 2
- Overfitting and regularization
- Regularization in scikit-learn
- Bias-variance tradeoff
- Cross-validation
- Ensemble learning and Random forests
Readings:
Hal Daumé III, A course in Machine Learning
- Ch. 5 Practical issues, sec. 5.0-5.6 (p.55-66), except precision-recall curves, ROC curves and AUC curves.
Jurafsky and Martin, Speech and language processing, 3rd ed. draft, 12. Jan. 2022
- Ch. 5, sec. 5.7 Regularization
- except the last paragraph starting with "Both L1 and L2..."
- Ch. 4, sec 4.7 "Evaluation: Precision, Recall, F-measure"
- Ch. 4, sec 4.8 "Test sets and Cross-validation"
Marsland
- Ch 2, sec 2.5 (Not the formulas)
- Ch 13: Introduction, 13.2 Bagging, 13.3 Random forest
<We plan to recommend some additional supplementary readings>
Group sessions
There are no new weekly exercises for this week. The program this week is to work on mandatory 2.