The Challenges and Opportunities of Continual Learning in Real-Time Machine Learning

The Challenges and Opportunities of Continual Learning in Real-Time Machine Learning

Snorkel AI via YouTube Direct link

Claypot

1 of 18

1 of 18

Claypot

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

The Challenges and Opportunities of Continual Learning in Real-Time Machine Learning

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

  1. 1 Claypot
  2. 2 Batch prediction vs. online prediction
  3. 3 Online prediction with batch features
  4. 4 Online prediction with online features
  5. 5 Train-predict inconsistency
  6. 6 "Easy" deployment: static
  7. 7 "Hard" deployment: continual
  8. 8 4 stages of continual learning
  9. 9 Smart triggers for retraining
  10. 10 Continual deployment challenges
  11. 11 Fresh data challenge
  12. 12 Algorithm challenge
  13. 13 Evaluation challenge
  14. 14 Real-time monitoring vs. batch monitoring
  15. 15 What to monitor
  16. 16 Temporal shifts: time window scale matters
  17. 17 Monitoring features: challenges
  18. 18 Monitoring solutions

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.