Lecture 17 - Transformers
Presented by Joseph E. Gonzalez
- Slides (PDF, pptx)
- Recording
- Optional: Lecture 3: Architectures by Tatsunori Hashimoto, from Stanford CS336: Language Modeling from Scratch, for those who want to go deeper on transformer architectures
- Code (HTML, Colab, GitHub)
- Chapter 12 (Chapter 12 PDF, Web Reader) of Deep Learning Foundations and Concepts