Responsible AI
Fairness, safety, privacy and the law: building AI people can trust.
Advanced
Once the basics are comfortable.
Book
Advanced
↗ External site
Fairness and Machine Learning: Limitations and Opportunities
A free textbook on the ideas and limits of fairness in automated decision-making.
Barocas, Hardt and Narayanan
Book
Advanced
↗ External site
Interpretable Machine Learning
A free book on making black-box models explainable: interpretable models, feature importance, SHAP and more.
Christoph Molnar
Document
Advanced
↗ External site
NIST AI Risk Management Framework
The US standards body's voluntary framework for identifying and managing risks across the AI lifecycle.
NIST
Course
Advanced
↗ External site
Red Teaming LLM Applications
Find weaknesses in LLM applications before attackers do: prompt injection, data leaks and harmful outputs.
DeepLearning.AI and Giskard