Dyad SciML Tutorial - Model Discovery with Universal Differential Equations

Dyad SciML Tutorial - Model Discovery with Universal Differential Equations

JuliaHub via YouTube Direct link

00:29 - Setting Up the Component Library

2 of 26

2 of 26

00:29 - Setting Up the Component Library

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Dyad SciML Tutorial - Model Discovery with Universal Differential Equations

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

  1. 1 00:00 - Introduction to Model Discovery
  2. 2 00:29 - Setting Up the Component Library
  3. 3 00:42 - Installing Required Packages
  4. 4 01:21 - Creating the Simple Pot Model
  5. 5 01:43 - Understanding Model Components
  6. 6 02:08 - Heat Sources and Thermal Connections
  7. 7 03:05 - Running Initial Analysis
  8. 8 03:47 - Setting Up Julia Environment
  9. 9 04:16 - Comparing Simulation vs Experimental Data
  10. 10 05:57 - Identifying Missing Physics
  11. 11 06:29 - Creating the Thermal Neural Network Component
  12. 12 07:18 - Understanding Neural Network Parameters
  13. 13 08:01 - Defining UDE Inputs and Outputs
  14. 14 09:17 - Creating the Neural Pot Model
  15. 15 10:29 - Incorporating the Neural Network
  16. 16 11:44 - Setting Up Training Analysis
  17. 17 13:33 - Training the UDE Model
  18. 18 14:03 - Training Results and Convergence
  19. 19 14:28 - Analyzing Convergence Plots
  20. 20 14:52 - Evaluating Calibrated Simulation Results
  21. 21 15:50 - Validation Against Experimental Data
  22. 22 16:06 - Symbolic Regression for Physics Discovery
  23. 23 17:07 - Understanding UDE Analysis Results
  24. 24 17:31 - Interpreting Candidate Models
  25. 25 18:31 - Selecting Physically Meaningful Models
  26. 26 19:26 - Summary and Key Takeaways

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.