Deep Ensembles: A Loss Landscape Perspective

Deep Ensembles: A Loss Landscape Perspective

Launchpad via YouTube Direct link

Intro

1 of 10

1 of 10

Intro

Class Central Classrooms beta

YouTube playlists curated by Class Central.

Classroom Contents

Deep Ensembles: A Loss Landscape Perspective

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

  1. 1 Intro
  2. 2 Overview
  3. 3 Hypothesis
  4. 4 Background Research
  5. 5 Measuring function similarity within and
  6. 6 Subspace sampling within and across trajectories
  7. 7 Loss and function similarity in prediction space
  8. 8 Evaluating the effects of ensembling and
  9. 9 Conclusion
  10. 10 Questions, comments, ideas

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.