Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Change for the Better: Improving Predictions by Automating Drift Detection in Machine Learning Models
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Predictive maintenance enables downtime to be scheduled rather than disruptive.
- 3 Development Operations principles reduce complexity.
- 4 Production system architecture mirrors the stages of the ML Ops cycle.
- 5 Off the shelf components minimize development effort.
- 6 Physics-based simulation allows realistic data generation.
- 7 AutoML "automagically" finds the right model.
- 8 Data drift can be visualized, interpreted and assessed.
- 9 Model-based labeling system is high fidelity.
- 10 The train-deploy-monitor-label cycle automatically works on its own.
- 11 Automate the entire ML Ops cycle and your machine learning models can change for the better, by themselves.
