Interpretable AI

8 Fairness and mitigating bias

This chapter covers

• Identifying sources of bias in datasets
• Validating whether machine learning models are fair using various fairness notions
• Applying interpretability techniques to identify the source of discrimination in machine learning models
• Mitigating bias using preprocessing techniques
• Documenting datasets using datasheets to improve transparency and accountability and to ensure compliance with regulation

You have learned a lot so far and have added a lot of interpretability techniques to your toolkit, ranging from those that you can use to interpret model processing (chapters 2 to 5) to those for interpreting representations learned by a machine learning model (chapters 6 and 7). We will now employ some ...