The Information Knot - Tying Sensing and Action; Emergence Theory of Representation Learning

The Information Knot - Tying Sensing and Action; Emergence Theory of Representation Learning

NYU Tandon School of Engineering via YouTube Direct link

Introduction

1 of 27

1 of 27

Introduction

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

The Information Knot - Tying Sensing and Action; Emergence Theory of Representation Learning

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

  1. 1 Introduction
  2. 2 Background
  3. 3 Tenets
  4. 4 Overview
  5. 5 Representation
  6. 6 sufficiency
  7. 7 information bottleneck
  8. 8 the task
  9. 9 mutual information
  10. 10 cost functional
  11. 11 Representation of Past Data
  12. 12 Two Information bottlenecks
  13. 13 Results
  14. 14 Disentangling
  15. 15 Bias
  16. 16 Leibler divergence
  17. 17 Flat minima
  18. 18 Biasvariance tradeoff
  19. 19 Notation
  20. 20 Pocket Planck Equation
  21. 21 Limit Cycles
  22. 22 Eigen Values
  23. 23 Local Entropy
  24. 24 Local Entropy Solution
  25. 25 Standard Gaussian Relaxation
  26. 26 Where do we take this
  27. 27 What does the steering not cover

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.