Meta-Learning - Why It’s Hard and What We Can Do - Ke Li

Meta-Learning - Why It’s Hard and What We Can Do - Ke Li

Institute for Advanced Study via YouTube Direct link

Intervals

24 of 30

24 of 30

Intervals

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Meta-Learning - Why It’s Hard and What We Can Do - Ke Li

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

  1. 1 Introduction
  2. 2 HighParameter Optimization
  3. 3 Automatic Model Selection
  4. 4 Program Induction
  5. 5 Design Considerations
  6. 6 Proof
  7. 7 Framework
  8. 8 Optimization Based Mental Learning
  9. 9 Objective Functions
  10. 10 Preventing Overfitting
  11. 11 Forward Dynamics
  12. 12 Uncertainty
  13. 13 Forward Dynamic Stochastic
  14. 14 Original Formulation
  15. 15 New Formulation
  16. 16 Expectation
  17. 17 Setting
  18. 18 Example
  19. 19 Quick Question
  20. 20 Update Formula
  21. 21 NeuralNets
  22. 22 Experiments
  23. 23 Parameters
  24. 24 Intervals
  25. 25 Gradients
  26. 26 Illustration
  27. 27 Outputs
  28. 28 empirical learning
  29. 29 correct yourself
  30. 30 speed up

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.