This course on AI Bias and Fairness aims to teach learners about the concept of bias in machine learning, its implications at different stages of the AI life cycle, and methods to mitigate biases in models and datasets. The course covers taxonomy types of common biases, interpretation-driven biases, data-driven biases like class imbalance, and techniques such as automated debiasing and adaptive latent space debiasing. The teaching method includes lectures with a focus on real-world examples and strategies for evaluating and reducing racial and gender bias. This course is intended for individuals interested in understanding and promoting fairness and equity in AI systems.
Overview
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
Taught by
https://www.youtube.com/@AAmini/videos
