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