Schedule

Required readings slides are listed below for each module. Readings from [ISLR] are always required while those from [ESL] are optional and supplemental.

All lecture slides as .qmd files are available here.

R code for all lectures is available here.

Handouts for some lectures (coding files, pdfs) are available here.

Instructions to create .pdfs of the lecture slides (works in Google Chrome or Chromium).

  1. Open some Slides in the browser.
  2. Toggle into Print View by pressing the E key. (It may not appear that anything has happened)
  3. Open the Print dialog: CTRL / CMD + P.
  4. Change the Destination setting to Save as PDF.
  5. Change the Layout to Landscape.
  6. Change the Margins to None.
  7. Enable the Background graphics option.
  8. Click Save ๐ŸŽ‰

0 Introduction and Review

Required reading below is meant to reengage brain cells which have no doubt forgotten all the material that was covered in STAT 306 or CPSC 340. We donโ€™t presume that you remember all these details, but that, upon rereading, they at least sound familiar. If this all strikes you as completely foreign, this class may not be for you.

Required reading
[ISLR] 2.1, 2.2, and Chapter 3 (this material is review)
Optional reading
[ESL] 2.4 and 2.6
Handouts
Programming in R .Rmd, .pdf
Using in RMarkdown .Rmd, .pdf
Date Slides Deadlines
03 Sep 24 (no class, Imagine UBC)
05 Sep 24 Intro to class, Git (Quiz 0 due tomorrow)
10 Sep 24 Understanding R / Rmd Lab 00, (Labs begin)
12 Sep 24 LM review, LM Example

1 Model Accuracy

Topics
Model selection; cross validation; information criteria; stepwise regression
Required reading
[ISLR] Ch 2.2 (not 2.2.3), 5.1 (not 5.1.5), 6.1, 6.4
Optional reading
[ESL] 7.1-7.5, 7.10
Date Slides Deadlines
17 Sep 24 Regression function, Bias and Variance
19 Sep 24 Risk estimation
24 Sep 24 Info Criteria
26 Sep 24 Practical model/variable selection HW 1 due

2 Regularization, smoothing, and trees

Topics
Ridge regression, lasso, and related; linear smoothers (splines, kernels); kNN
Required reading
[ISLR] Ch 6.2, 7.1-7.7.1, 8.1, 8.1.1, 8.1.3, 8.1.4
Optional reading
[ESL] 3.4, 3.8, 5.4, 6.3
Date Slides Deadlines
1 Oct 24 Ridge, Lasso
3 Oct 24 CV for comparison, NP 1
8 Oct 24 NP 2, Why smoothing?
10 Oct 23 Other

3 Classification

Topics
logistic regression; LDA/QDA; naive bayes; trees
Required reading
[ISLR] Ch 2.2.3, 5.1.5, 4-4.5, 8.1.2
Optional reading
[ESL] 4-4.4, 9.2, 13.3
Date Slides Deadlines
15 Oct 24 Classification, LDA and QDA
17 Oct 24 Logistic regression, Gradient descent HW 2 due
22 Oct 24 Nonlinear, Other losses
24 Oct 24 The bootstrap

4 Modern techniques

Topics
bagging; boosting; random forests; neural networks
Required reading
[ISLR] 5.2, 8.2, 10.1, 10.2, 10.6, 10.7
Optional reading
[ESL] 10.1-10.10 (skip 10.7), 11.1, 11.3, 11.4, 11.7
Date Slides Deadlines
29 Oct 24 Bagging and random forests, Boosting
31 Oct 24 Intro to neural nets HW 3 due
5 Nov 24 Estimating neural nets
7 Nov 24 More neural nets (TBD), Optional NNet handout
12 Nov 24 No class. (Midterm break)
14 Nov 24 Neural nets wrapup

5 Unsupervised learning

Topics
dimension reduction and clustering
Required reading
[ISLR] 12
Optional reading
[ESL] 8.5, 13.2, 14.3, 14.5.1, 14.8, 14.9
Date Slides Deadlines
19 Nov 24 Intro to PCA, Issues with PCA HW 4 due
21 Nov 24 PCA v KPCA
26 Nov 24 K means clustering
28 Dec 24 Hierarchical clustering
3 Dec 24 Topic TBD and/or Review
5 Dec 24 Review HW 5 due

F Final exam

Important

Do not make any plans to leave Vancouver before the final exam date is announced.

  • In person attendance is required (per Faculty of Science guidelines)
  • You must bring your computer as the exam will be given through Canvas
  • Please arrange to borrow one from the library if you do not have your own. Let me know ASAP if this may pose a problem.
  • You may bring 2 sheets of front/back 8.5x11 paper with handwritten notes you want to use. No other materials will be allowed.
  • There will be no required coding, but I may show code or output and ask questions about it.
  • It will be entirely multiple choice / True-False / matching, etc. Delivered on Canvas.