Nonlinear Independent Component Analysis - Aapo Hyvärinen

Nonlinear Independent Component Analysis - Aapo Hyvärinen

Institute for Advanced Study via YouTube Direct link

Abstract

2 of 23

2 of 23

Abstract

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Nonlinear Independent Component Analysis - Aapo Hyvärinen

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

  1. 1 Intro
  2. 2 Abstract
  3. 3 Success of Artificial Intelligence
  4. 4 Neural networks
  5. 5 Deep learning
  6. 6 Importance unsupervised learning
  7. 7 ICA as principled unsupervised learning
  8. 8 Fundamental difference between ICA and PCA
  9. 9 Identifiability means ICA does blind source separation
  10. 10 Example of ICA: Brain source separation
  11. 11 Example of ICA: Image features
  12. 12 Nonlinear ICA is an unsolved problem
  13. 13 Darmois construction
  14. 14 Temporal structure helps in nonlinear ICA
  15. 15 Algorithmic trick: "Self-supervised" learning
  16. 16 Theorem: TCL estimates nonlinear nonstationary ICA Assume data follows nonlinear ICA model (t)-f s(tl) with
  17. 17 Permutation contrastive learning (Hyvärinen and Morioka 2017)
  18. 18 Illustration of demixing capability by PCL Non Gaussian AR model for sources
  19. 19 Extensions of nonlinear ICA on time series
  20. 20 General framework: Deep Latent Variable Models
  21. 21 Conditioning makes DLVM identifiable
  22. 22 Alternative approaches to DLVM case
  23. 23 Conclusion

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.