Learn about the growing field of MLOps and the modeling techniques used to monitor model drift and bias.
Overview
Syllabus
Introduction
- The need for model monitoring
- Setting up the exercise files
- ML models in production
- Challenges with serving models in production
- Metrics to monitor
- Data for model monitoring
- Introduction to model drift
- Concept drift
- Feature drift
- What causes drift?
- Drift remediation process
- Detecting concept drift
- Concept drift detection example
- Detecting feature drift
- Feature drift detection example
- Detecting drift in text and images
- Software for drift detection
- Drift monitoring pipeline
- Analyzing drift trends
- Discovering root causes for drift
- Retraining to overcome drift
- Fairness and bias
- Fairness in ML
- Sources of ML bias
- Protected attributes
- Demographic parity
- Bias detection techniques
- Equal opportunity score
- EOS example
- Bias detection software
- Overcoming bias in ML
- Next steps
Taught by
Kumaran Ponnambalam