Learning About the Physical World - Comparing Humans, Deep Neural Networks, and Probabilistic Programs

Learning About the Physical World - Comparing Humans, Deep Neural Networks, and Probabilistic Programs

MITCBMM via YouTube Direct link

Al technologies

2 of 17

2 of 17

Al technologies

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Learning About the Physical World - Comparing Humans, Deep Neural Networks, and Probabilistic Programs

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

  1. 1 Intro
  2. 2 Al technologies
  3. 3 The common-sense core Human thought is structured around a basic understanding of physical objects, intentional agents, and their interactions - intuitive physics (forces, masses...) and psychology (…
  4. 4 Common-sense scene understanding
  5. 5 The common sense core
  6. 6 Engineering the common-sense core?
  7. 7 Engineering the common-sense core Probabilistic programs
  8. 8 Intuitive physics in blocks world
  9. 9 (Battaglia, Hamrick, Tenenbaum, PNAS 2013) Probabilistic IPE
  10. 10 The intuitive physics engine (Battaglia, Hamrick. Tenenbaum, PNAS 2013)
  11. 11 Probabilistic dynamics in 12 month olds
  12. 12 Physical scene parsing
  13. 13 Theory building as program induction ( program-learning programs)
  14. 14 Development of physics in infants
  15. 15 Intuitive physics in the brain
  16. 16 Intuitive physics in neural circuits?
  17. 17 Conclusion The core of common sense: Human thought is structured around a basic understanding of physical objects, intentional agents, and their interactions

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.