Description
What is this course about?
This course focuses on the data-based and mathematical factors contributing to bias in generative AI. Join instructor Jazmia Henry as she explores how data curation, analytical techniques, and post-training constraints can mitigate harmful biases embedded in these models. Through real-world examples and case studies, the course aims to help you understand and apply strategies for creating fairer, more transparent AI systems.
This course is part of the learning path Building AI Products: Implementing Responsible AI Professional Certificate by LinkedIn Learning. Complete all courses and pass the final exam to earn a Professional Certificate you can add to your LinkedIn profile.
Objectives
What will I be able to do by the end of this course?
- Describe the data sources and mathematical assumptions behind generative AI that contribute to biased outcomes.
- Identify and evaluate biases in LLMs using data curation, statistical analysis, and counterfactuals.
- Implement practical techniques to constrain models post-deployment to reduce the risk of bias reintroduction.
- Apply parity metrics to measure and adjust bias levels in model outputs.
- List types of failures that have happened in case studies on biased language models and describe opportunities for improved training methods.
Audience
Who is this course for?
- Developers
- Technical program and product managers
- Engineering managers
Prerequisites
What do I need to know before taking this course?
- Experience with AI model development and evaluation
- Familiarity with basic statistical analysis and data curation techniques