AI Bias and Fairness

This lecture explains how algorithmic bias arises throughout the AI pipeline and presents methods for detecting and mitigating it. Topics include data and feature bias, class imbalance, latent-space debiasing, and evaluation across racial and gender subgroups.

Syllabus

- Introduction and motivation
- What does "bias" mean?
- Bias in machine learning
- Bias at all stages in the AI life cycle
- Outline of the lecture
- Taxonomy types of common biases
- Interpretation driven biases
- Data driven biases - class imbalance
- Bias within the features
- Mitigate biases in the model/dataset
- Automated debiasing from learned latent structure
- Adaptive latent space debiasing
- Evaluation towards decreased racial and gender bias
- Summary and future considerations for AI fairness