Completed
Presentation Outline
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Understanding Deep Learning Requires Rethinking Generalization
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Presentation Outline
- 3 Universal Approximation Theorem
- 4 L2 Regularization - "Weight Decay"
- 5 Dropout
- 6 Data Augmentation
- 7 Rondomization Tests
- 8 Results of Randomization Tests
- 9 Conclusions & Impications
- 10 Explicit Regularization Tests
- 11 Implicit Regularization Findings
- 12 Finite-Sample Expressivity of Neural Networks
- 13 Appeal to Linear Models
- 14 Investigating SGD
- 15 Final Conclusions
