Fall 2026 · Lecture 19 · November 9, 2026
Transformer
Learning contextual representations through attention and parallel sequence processing.
Learning goals
- Compute scaled dot-product attention conceptually.
- Explain queries, keys, and values.
- Identify the roles of multi-head attention and positional information.
Materials
Slides, code, examples, and references will be added after class.
Lecture notes
An attention walkthrough, architecture map, and shape annotations will be added here.
Lecture extensions
Course materials and optional topics
Four independently reviewed sections
Assignment pending
Develop the assigned part of the lecture’s core course materials.
The course team will assign this section through a GitHub issue.
Assignment pending
Develop the assigned part of the lecture’s core course materials.
The course team will assign this section through a GitHub issue.
Assignment pending
Develop an optional extension, application, or related topic assigned for this lecture.
The course team will assign this section through a GitHub issue.
Assignment pending
Develop an optional extension, application, or related topic assigned for this lecture.
The course team will assign this section through a GitHub issue.