Recent Developments in Over-parametrized Neural Networks, Part I

Recent Developments in Over-parametrized Neural Networks, Part I

Simons Institute via YouTube Direct link

Introduction

1 of 32

1 of 32

Introduction

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Recent Developments in Over-parametrized Neural Networks, Part I

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Introduction
  2. 2 Outline
  3. 3 Goals
  4. 4 Whats Hard
  5. 5 Whats Easy
  6. 6 Non convex optimization
  7. 7 Notation
  8. 8 Overparametrization
  9. 9 Experiments
  10. 10 Rule of Thumb
  11. 11 Theoretical Problem
  12. 12 Optimal Optimization
  13. 13 Taxonomy of Results
  14. 14 Skip Connections
  15. 15 Expressivity
  16. 16 Geometric Results
  17. 17 Geometry Results
  18. 18 Onepoint convexity
  19. 19 Taylors theorem
  20. 20 Royer algorithm
  21. 21 Randomness
  22. 22 Theorem
  23. 23 Secondorder Stationary Points
  24. 24 Neural Networks
  25. 25 Optimality Conditions
  26. 26 Global Optimal
  27. 27 Other Losses
  28. 28 NonDegenerate Critical Points
  29. 29 Three Strategies
  30. 30 Second Order Descent
  31. 31 Stationary Points
  32. 32 Learning Networks

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.