Course
Skills
Responsible AI for Developers: Interpretability & Transparency
This course introduces concepts of AI interpretability and transparency.
What you'll learn
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.
Table of contents
Course Introduction
1min
AI Interpretability & Transparency
47mins
- Overview of interpretability and transparency 5m
- Overview of interpretability techniques 7m
- Feature based explanations: Model agnostic 11m
- Feature based explanations: Model specific 7m
- Concept-based and example-based explanations 5m
- Tools for interpretability 5m
- Data and Model Transparency 6m
- Lab: Vertex Explainable AI 1m
- Lab: Explaining an Image Classification Model with Vertex Explainable AI 0m
Course Summary
2mins
