8 Teaching Materials
This page collects resources for instructors using Machine Learning from Human Preferences in their courses. The materials below were developed for Stanford’s CS329H but can be adapted to courses of varying length and focus.
8.1 Lecture Slides
Each chapter has an accompanying slide deck in RevealJS format.
| Chapter | Topic | Slides |
|---|---|---|
| Introduction | Overview and motivation | Slides |
| Chapter 1 | Foundations | Slides |
| Chapter 2 | Learning | Slides |
| Chapter 3 | Elicitation | Slides |
| Chapter 4 | Decisions | Slides |
| Chapter 5 | Aggregation | Slides |
| Chapter 6 | Whose? | Slides |
8.2 Problem Sets
| Problem Set | Topics |
|---|---|
| Problem Set 1 | Foundations |
| Problem Set 2 | Learning |
| Problem Set 3 | Elicitation |
| Problem Set 4 | Decisions |
8.3 Suggested Course Pathways
The book supports several course configurations depending on audience and length. Chapter 1 is foundational to all pathways.
- Applied AI (e.g., early graduate ML course): Chapters 1, 2, and 4.
- Discrete choice and economics: Skim Chapter 1, then Chapters 2 and 4.
- Deep learning focus: Chapters 2–4.
- Computation and society: Chapters 1, 5, and 6.