Lecture Plan and Progress
Topics covered:
- main parts of chapters 1-7, 9, 13 and 14
- possibly selected topics from the rest of the book
- asymptotic estimation theory (handouts, copies from other books)
- empirical Bayes theory (handouts, copies from other books)
Preliminary plan and progress:
| Week | Chapter | Topic | Download | Remark |
|---|---|---|---|---|
| 2 | Ch. 1 | Introductory meeting | Introductory slides | Decision on lecture times |
| 3 | Ch. 2 | Overview of supervised learning | 4 hrs lecture (no exercises) | |
| 4 | Ch. 3.1-3.4.1 | Linear methods for regression | ||
| 5 | Rest of Ch. 3, except 3.7-3.8 | Linear methods for regression | ||
| 6 | Ch. 4, except 4.4.3 and 4.5.2 | Linear methods for classification | 4.4.3 is covered in TMA4315 Generalized linear models | |
| 7 | Ch. 5, except 5.8, 5.9 and Appendix | Basis expansions and regularization | Splines (and smoothing splines) are nicely covered in the book "Generalized Additive Models" by Hastie and Tibshirani | |
| 8 | Ch. 6 | Kernel smoothing methods | Kernel density estimation | |
| 9 | Ch. 7.1-7.6 (7.7, 7.8, 7.9 and 7.12 are not in curriculum) | Model assessment and selection | ||
| 10 | Ch. 7.10-7.11 and some remaining issues from 7.1-7.6. 8.1.8.2 | Model selection and inference | ||
| 11 | Ch. 8.5 (8.5.1 and 8.5.2) | Maximum likelihood estimation and asymptotic estimation theory | Bookchapter on large sample theory | Ch. 8.5.1-8.5.2 plus the book chapter will be taught |
| 12 | Download trial exam from Message list on March 22 | Trial exam, no lectures | ||
| 13 | Empirical Bayes theory | Casella: An introduction to empirical Bayes data analysis (article), Chapter on Stein's paradox | Discussion of trial exam | |
| 14 | Ch. 9.1, 9.2. 9.4 | Generalized additive models (GAM), Classification and regression trees (CART), Multivariate adaptive regression splines (MARS) | ||
| 15 | Selected topics for discussion | Final lecture |