In this course, students will learn how to approach and apply ethical AI. Coursework will enable practitioners to design and build models with enhanced fairness and limited bias to avoid unforeseen consequences and connect ethical AI concepts to critical issues in privacy, governance, transparency, and security. They’ll begin with acquiring ethical AI literacy skills that will enable them to engage in more meaningful discussions across AI disciplines and learn how to apply ethical AI principles to their organization. Students will then learn how to implement technical measures toward bias, fairness, and explainability to help ensure an ethical future for all.
Overview
Syllabus
- Introduction to Ethical AI
- Learn the fundamentals of AI Ethics, including the definitions, history, context, and stakeholders involved with this domain!
- AI Ethics for Organizations
- Learn how to articulate and apply ethical AI for organizations and businesses, including how bias applies to organizations, ethical AI principles and programs, and guardrails!
- Identifying Bias Towards Fairness
- Learn how to identify the different types of AI biases and harms, and apply harm quantification metrics for evaluating fairness!
- Mitigating Bias Towards Fairness
- Learn how to mitigate bias, including comparisons between strategies and metrics, and applying techniques toward enhancing fairness!
- Transparency, Trust, and Explainability
- Learn how to articulate context around AI regulations, data governance, and auditing! Along the way, you will also learn how to apply techniques for transparency and explainability.
- AI Ethics for Personalized Budget Prediction
- Test your skills for identifying the ethical impact of a use case! You'll perform quantitative analyses, mitigate bias, and create a model card to document the ethical impact and your findings!
Taught by
cd1827 Ria Cheruvu
