DDPS - A Flexible and Generalizable XAI Framework for Scientific Deep Learning

DDPS - A Flexible and Generalizable XAI Framework for Scientific Deep Learning

Inside Livermore Lab via YouTube Direct link

Intro

1 of 19

1 of 19

Intro

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

DDPS - A Flexible and Generalizable XAI Framework for Scientific Deep Learning

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

  1. 1 Intro
  2. 2 Deep learning in physics-based systems
  3. 3 Scientific modeling in the age of Al
  4. 4 Lots of data BUT not enough!
  5. 5 Out-of-distribution (OOD) generalization
  6. 6 Interpretable and explainable Al (XAI)
  7. 7 Key idea: Integral equations!
  8. 8 Theory-guided machine learning
  9. 9 Functional data analysis (FDA)
  10. 10 Applications
  11. 11 Motivation example: 1D
  12. 12 Predicting strain energy from heterogeneous material property
  13. 13 Predicting velocity field from heterogeneous permeability
  14. 14 Summary: towards interpretable and generalizable deep learning
  15. 15 Acknowledgments
  16. 16 Example 3: Predicting high-fidelity wall shear stress (WSS) from low-fidelity velocity
  17. 17 Example 5: Local interpretation: Predicting velocity field from permeability fields
  18. 18 Appendix: Library
  19. 19 Generalized functional data analysis (gFDA)

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.