Completed
- Intro & Overview
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Grokking - Generalization Beyond Overfitting on Small Algorithmic Datasets
Automatically move to the next video in the Classroom when playback concludes
- 1 - Intro & Overview
- 2 - The Grokking Phenomenon
- 3 - Related: Double Descent
- 4 - Binary Operations Datasets
- 5 - What quantities influence grokking?
- 6 - Learned Emerging Structure
- 7 - The role of smoothness
- 8 - Simple explanations win
- 9 - Why does weight decay encourage simplicity?
- 10 - Appendix
- 11 - Conclusion & Comments
