This course introduces concepts of AI interpretability and transparency. It discusses the importance of AI transparency for developers and engineers. It explores practical methods and tools to help achieve interpretability and transparency in both data and AI models.
Overview
Syllabus
- Course Introduction
- Course Introduction
- AI Interpretability & Transparency
- Overview of interpretability and transparency
- Overview of interpretability techniques
- Feature based explanations: Model agnostic
- Feature based explanations: Model specific
- Concept-based and example-based explanations
- Tools for interpretability
- Data and Model Transparency
- Lab: Vertex Explainable AI
- Explaining an Image Classification Model with Vertex Explainable AI
- Quiz
- Course Summary
- Course Summary
- Reading
- Course Resources
- Module 0: Course Introduction
- Module 1: AI Interpretability & Transparency
- Module 2: Course Summary
- Your Next Steps
- Course Badge
