Ekya - Continuous Learning of Video Analytics Models on Edge Compute Servers

Ekya - Continuous Learning of Video Analytics Models on Edge Compute Servers

USENIX via YouTube Direct link

Key Takeaways

12 of 16

12 of 16

Key Takeaways

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Ekya - Continuous Learning of Video Analytics Models on Edge Compute Servers

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

  1. 1 Intro
  2. 2 Video data is everywhere
  3. 3 Why video analytics at the edge?
  4. 4 Edge Video Analytics Setup
  5. 5 The cost of continuous learning
  6. 6 Resource demands of continuous learn
  7. 7 Summary thus far
  8. 8 Scheduling decisions to make
  9. 9 Working Example
  10. 10 Example - Fair Scheduler
  11. 11 Example - a smarter schedule
  12. 12 Key Takeaways
  13. 13 Ekya Design
  14. 14 Ekya Thief Scheduler Goal: Maximize mean inference accuracy across all jobs
  15. 15 Evaluation
  16. 16 Scaling with increasing video streams

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.