Deep Ensembles: A Loss Landscape Perspective

Deep Ensembles: A Loss Landscape Perspective

Yannic Kilcher via YouTube Direct link

- Intro & Overview

1 of 14

1 of 14

- Intro & Overview

Class Central Classrooms beta

YouTube videos 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 & Overview
  2. 2 - Deep Ensembles
  3. 3 - The Solution Space of Deep Networks
  4. 4 - Bayesian Models
  5. 5 - The Ensemble Effect
  6. 6 - Experiment Setup
  7. 7 - Solution Equality While Training
  8. 8 - Tracking Multiple Trajectories
  9. 9 - Similarity of Independent Solutions
  10. 10 - Comparison to Baselines
  11. 11 - Weight Space Cross-Sections
  12. 12 - Diversity vs Accuracy
  13. 13 - Comparing Ensembling Methods
  14. 14 - Conclusion & Comments

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.