Completed
- What's Wrong With Black-Box Predictions
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
ML Testing & Explainability - Full Stack Deep Learning - Spring 2021
Automatically move to the next video in the Classroom when playback concludes
- 1 - What's Wrong With Black-Box Predictions
- 2 - Types of Software Tests
- 3 - Software Testing Best Practices
- 4 - Sofware Testing In Production
- 5 - Continuous Integration and Continuous Delivery
- 6 - Testing Machine Learning Systems
- 7 - Infrastructure Tests
- 8 - Training Tests
- 9 - Functionality Tests
- 10 - Evaluation Tests
- 11 - Shadow Tests
- 12 - A/B Tests
- 13 - Labeling Tests
- 14 - Expectation Tests
- 15 - Challenges and Solutions Operationalizing ML Tests
- 16 - Overview of Explainable and Interpretable AI
- 17 - Use An Interpretable Family of Models
- 18 - Distill A Complex To An Interpretable One
- 19 - Understand The Contribution of Features To The Prediction
- 20 - Understand The Contribution of Training Data Points To The Prediction
- 21 - Do You Need "Explainability"?
- 22 - Caveats For Explainable and Interpretable AI