For the full video of this presentation, please visit: https://www.edge-ai-vision.com/2022/09/responsible-ai-and-modelops-in-industry-practical-challenges-and-lessons-learned-a-presentation-from-fiddler-ai/
Krishnaram Kenthapadi, Chief Scientist at Fiddler AI, presents the “Responsible AI and ModelOps in Industry: Practical Challenges and Lessons Learned” tutorial at the May 2022 Embedded Vision Summit.
How do we develop machine learning models and systems taking fairness, explainability and privacy into account? How do we operationalize models in production, and address their governance, management and monitoring? Model validation, monitoring and governance are essential for building trust and adoption of computer-vision-based AI systems in high-stakes domains such as healthcare and autonomous driving.
In this presentation, Kenthapadi first motivates the need for adopting a “responsible AI by design” approach when developing AI/ML models and systems for different consumer and enterprise applications. He then focuses on the application of responsible AI and ModelOps techniques in practice through industry case studies. He discusses the sociotechnical dimensions and practical challenges, and concludes with the key takeaways and open challenges.
17. Integrated Gradients for Explaining Diabetic
Retinopathy Predictions
Retinal Fundus Image
Integrated Gradients for label: “proliferative”
Visualization: Overlay heatmap on green channel
Lesions
Neovascularization
● Hard to see on original image
● Known to be vision-threatening
Can attributions help doctors better
diagnose diabetic retinopathy? 17
38. MPM is to MLOps as
Similar
Application
Performance Mgmt.
APM is to DevOps
MPM
Monitoring
Explainability Continuous
Monitoring &
Central Controls
Model
Performance
Mgmt
Explainability Fairness
Model Performance Management is
a Framework for Operationalizing AI/ML