Learning How to Break Symmetry With Symmetry-Preserving Neural Networks - IPAM at UCLA

Learning How to Break Symmetry With Symmetry-Preserving Neural Networks - IPAM at UCLA

Institute for Pure & Applied Mathematics (IPAM) via YouTube Direct link

General questions

24 of 31

24 of 31

General questions

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Learning How to Break Symmetry With Symmetry-Preserving Neural Networks - IPAM at UCLA

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

  1. 1 Intro
  2. 2 Overview
  3. 3 Why is symmetry useful
  4. 4 Invariant vs equivariant models
  5. 5 Equivariant methods
  6. 6 Global symmetry equivalent
  7. 7 Questions
  8. 8 Applications
  9. 9 Molecular force fields
  10. 10 Scaling
  11. 11 Longrange interactions
  12. 12 Predicting charge density
  13. 13 Using a neural network
  14. 14 First paper
  15. 15 Competition
  16. 16 Efficiency
  17. 17 Advanced properties
  18. 18 Neural networks
  19. 19 Representation theory
  20. 20 Reducible representation
  21. 21 Future spaces
  22. 22 Spherical harmonic projections
  23. 23 Invariance
  24. 24 General questions
  25. 25 Emergent behavior
  26. 26 Curious principle
  27. 27 Structural phase transitions
  28. 28 First case
  29. 29 Order parameters
  30. 30 Why not just train a model
  31. 31 Another example

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.