Skip to main content

Pre-Alpha This lesson is in the pre-alpha phase, which means that it is in early development, but has not yet been taught.

Trustworthy AI: Explainability, Bias, Fairness, and Safety

Trustworthy AI: Explainability, Bias, Fairness, and Safety
Key Points
Glossary
Learner Profiles
- Reference

Search the All In One page

Trustworthy AI: Explainability, Bias, Fairness, and Safety

%

Instructor View

EPISODES

Summary and Setup

1. Overview

2. Preparing to train a model

3. Model evaluation and fairness

4. Model fairness: hands-on

5. Interpretablility versus explainability

6. Explainability methods overview

7. Explainability methods: deep dive

8. Explainability methods: linear probe

9. Explainability methods: GradCAM

10. Estimating model uncertainty

11. OOD detection: overview, output-based methods

12. OOD detection: distance-based and contrastive learning

13. OOD detection: training-time regularization

14. Documenting and releasing a model

Key Points
Glossary
Learner Profiles
Reference

See all in one page

Learner Profiles

This is a placeholder file. Please add content here.

This lesson is subject to the Code of Conduct

Edit on GitHub | Contributing | Source

Cite | Contact | About

Materials licensed under CC-BY 4.0 by the authors

Template licensed under CC-BY 4.0 by The Carpentries

Built with sandpaper (0.16.9), pegboard (0.7.6), and varnish (1.0.4)