Hand-outs MA8701V2023
All files used in the teaching are available as a github repo: https://github.com/mettelang/MA8701V2023
Lecture notes (html-version) and what we have written in class (pdf) will be available from this page. (These files are of cause also available directly from the github repo, but html-files are not rendering well directly from github - so a local clone of the repo at IMF is used to show the html-files and to be in full control of the rendering. ) If you prefer a pdf-file to the html-file, this file is (nearly always) at the same place as the the htmo-just replace by pdf (so e.g L1.pdf in place of L1.html with the long address in front).
L=lecture and W=week.
| Date | Part | Session | Topic | Description | Links |
|---|---|---|---|---|---|
| 24.04 | 5 | L22 (S21) | Finish reviewing the course | Course overview with focus on the oral exam | L22inclass.pdf |
| 14+17+21.04 | 5 | Article presentations | |||
| 14.04 | 5 | L21 (S21) | Start reviewing the course | Learning goals and data analysis project | L21inclass.pdf |
| 27.03 | 4 | L20 (S21) | XAI v/Kjersti Aas | Shapley | L20notes.html and slide set on Blackboard |
| 24.03 | 4 | L19 (zoom) | XAI v/Kjersti Aas | Lime and counterfactuals | L19notes.html and slide set on Blackboard |
| 20.03 | 4 | L18 (zoom) | XAI v/Kjersti Aas | Introduction | L18notes.html and slide set on Blackboard |
| 13.03 | 3 | L17 | Ensembles | Statistical inference | L17v2.html , L17v2inclass.pdf (added after class) |
| 10.03 | 3 | L16 | Ensembles | Hyperparameter tuning | L16.html , L16inclass.pdf (added after class) |
| 06.03 | 3 | L15 | Ensembles | Ensembles | L15.html , L15inclass2023.pdf (added after class) |
| 03.03 | 3 | No lecture | Ensembles | XGBoost | Watch video by Berent Lunde video and slides |
| 27.02 | 3 | L14 | Ensembles | Boosting | L14inclass2023.pdf (added after class), AdaBoostproof:AdaboostFSExploss.pdf and Exercise 10.2 of ESL |
| 24.02 | 3 | L13 | Ensembles | Bagging, trees, random forests | L13.html and L13inclass.pdf (added after class) |
| 13.02+ | 2 | W6=L11+12 | Shrinkage and regularization | Statistical inference | W6.html (updated 2023.02.19) and L11inclass.pdf and L12inclass.pdf |
| 10.02 | 2 | L10 | Shrinkage and regularization | Lasso logistic regression | L10.html and L10notes.pdf (added after class) |
| 06.02 | 2 | L9 | Shrinkage and regularization | Lasso regression variants | L9.html and L9beamer20230206.pdf (added after class) |
| 03.02 | 2 | L8 | Shrinkage and regularization | Lasso regression | L8.html and L8liveinclass.pdf (added after class) |
| 30.01 | 2 | L7 | Shrinkage and regularization | Linear model and ridge regression | L7.html and L7beamer20230130.pdf (added after class) |
| 23.01+27.01 | 1 | W3=L5+6 | Introduction and core concepts | Missing data in statistical analysis | W3.html (updated 2023.01.27) and L5beamer20230123.pdf and L6beamer20230127.pdf |
| 16.01+20.01 | 1 | W2=L3+4 | Introduction and core concepts | Study optimism of the training error rate from in-sample error | W2.html and L3beamer20230116.pdf and L4beamer20230120.pdf (added after class) |
| 13.01 | 1 | L2 | Introduction and core concepts | Decision theory, classification, bias-variance trade-off, Err | L2.html and L2beamer20230113REv.pdf (added after class) |
| 09.01 | 1 | L1 | Introduction and core concepts | Assumed background knowledge, getting to know each other and the plans ahead, new material on decision theory | L1.html and L1beamer20230109inclass.pdf (added after class) |