Course

Artificial Intelligence (AI) has the potential to transform our lives, but it’s not without challenges. One critical issue is AI bias, where systems unintentionally or intentionally produce unfair outcomes that reflect human prejudices. This module explores how bias enters AI, the impact it can have on individuals and society, and why addressing it is essential for creating ethical, trustworthy systems. Let’s explore how bias starts, how it can affect AI systems, and what steps we can take to ensure AI serves everyone fairly.  

In Module 1, we cover the following Lessons:

In Module 2, we cover the following Lessons:

Lesson 2.4: Bias in Hiring Algorithms - The Case of Amazon and Beyond

Lesson 2.5: Bias in Government Fraud Detection Systems - Cases in the UK and Netherlands

Lesson 2.6: Key Takeaways and Warnings

Lesson 2.7: Poisoning ML Systems with Non-Randomness

In Module 3, we cover the following Lessons:

In Module 4, we cover: 

Lesson 4.1: Introduction to Explainable AI

Lesson 4.2: Why Explainability Matters in AI

Lesson 4.3.: XAI Tools and Methods

Lesson 4.4.: Practical Steps for Implementing XAI

Lesson 4.5: Challenges and Future Directions in XAI Implementation

Lesson 4.6: Situation Aware explainability (SAX)

Lesson 4.7: Consolidating XAI Knowledge

Serving as a visual catalog, it facilitates exploration, comparison, and informed tool selection, thereby fostering a more effective approach to bias mitigation. Additionally, Bias Detector Toolkit is a part of VUF, where we are developing bias detection tools for specific contexts of use cases on the project, and will be presented in a later edition of MOOC.

The Virtualized Unbiasing Framework is a holistic application focused on explaining AI bias and equipping  developers with an easy-to-navigate and visually organized catalog. It  consists of the scrollytelling application, real life examples and the catalog of methods and tools  for bias mitigation.

In Module 5, we cover:

Lesson 5.1: Scrollytelling Application

Lesson 5.2: Stages of AI Trainings

Lesson 5.3: Real Life Examples

Lesson 5.4: Catalog of Bias Detection and Mitigation Strategies

As AI becomes a bigger part of our daily lives, ensuring that these systems are fair is more important than ever. AI fairness means designing systems that treat everyone equally, regardless of their background, identity, or circumstances. Fairness in AI requires diverse, unbiased data, thoughtful design, and ongoing evaluation to ensure systems make equitable and trustworthy decisions. 

In the context of the Horizon Europe MAMMOth project, the “AI Fairness Definition Guide” was developed to help those creating AI understand how to define fairness in the social context of their created systems by working with stakeholders and experts from other disciplines. The guide presents a workflow for gathering fairness concerns of affected stakeholders and using them to derive corresponding formalisms and practices under a combined computer, social, and legal science viewpoint.

In Module 6, we cover:

Lesson 6.1: Understanding AI Fairness