Materials

Textbooks and Key Resources

Recommended Books

• Fairness and Machine Learning by Barocas, Hardt, and Narayanan - Available online
• The Ethical Algorithm by Kearns and Roth
• Interpretable Machine Learning by Christoph Molnar - Available online

Online Courses

• Practical Data Ethics by fast.ai
• AI Ethics on Coursera

Tools and Frameworks

Fairness

• Fairlearn - Python toolkit for assessing and improving fairness
• AIF360 - IBM’s AI Fairness 360 toolkit
• What-If Tool - Visual tool for ML model analysis

Explainability

• LIME - Local Interpretable Model-agnostic Explanations
• SHAP - SHapley Additive exPlanations
• Captum - Model interpretability for PyTorch

Privacy

• TensorFlow Privacy - Differential privacy in TensorFlow
• Opacus - Differential privacy training for PyTorch
• PySyft - Privacy-preserving ML

Programming Resources

• Python: If you need a refresher, try Python Data Science Handbook
• Machine Learning: Scikit-learn tutorials
• Deep Learning: PyTorch tutorials or TensorFlow tutorials

Important Papers and Articles

Foundational Papers

• Gebru et al., “Datasheets for Datasets”
• Mitchell et al., “Model Cards for Model Reporting”
• Buolamwini & Gebru, “Gender Shades”

Policy and Governance

• EU AI Act
• NIST AI Risk Management Framework

Additional Resources

• AI Ethics Guidelines Global Inventory
• Papers with Code - Ethics
• ACM Conference on Fairness, Accountability, and Transparency (FAccT)