DreamCoder- Growing Generalizable, Interpretable Knowledge With Wake-Sleep Bayesian Program Learning

DreamCoder- Growing Generalizable, Interpretable Knowledge With Wake-Sleep Bayesian Program Learning

Yannic Kilcher via YouTube Direct link

- Experimental Results on LOGO Drawings

7 of 11

7 of 11

- Experimental Results on LOGO Drawings

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

DreamCoder- Growing Generalizable, Interpretable Knowledge With Wake-Sleep Bayesian Program Learning

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

  1. 1 - Intro & Overview
  2. 2 - DreamCoder System Architecture
  3. 3 - Wake Phase: Neural Guided Search
  4. 4 - Abstraction Phase: Extending the Internal Library
  5. 5 - Dreaming Phase: Training Neural Search on Fictional Programs and Replays
  6. 6 - Abstraction by Compressing Program Refactorings
  7. 7 - Experimental Results on LOGO Drawings
  8. 8 - Ablation Studies
  9. 9 - Re-Discovering Physical Laws
  10. 10 - Discovering Recursive Programming Algorithms
  11. 11 - Conclusions & Discussion

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.