MIT RES.EC-001 Exploring Fairness in Machine Learning, Spring 2020 - Fairness Criteria, Exploring Fairness in Machine Learning

Unlock Ethical AI: Navigating Fairness and Bias in Machine Learning with MIT Experts!

4.0 (0)

8 learners

What you'll learn

Understand the ethical considerations in machine learning.
Explore methods for ensuring fairness in machine learning models.
Analyze case studies to identify and address bias in datasets.
Apply fairness criteria to improve machine learning algorithm equity.

This course includes

1.3 hours of video
Certificate of completion
Access on mobile and TV

Summary

Keywords

confusion matrix demographic parity equalized odds equalized opportunity fairness res-ec-001-exploring-fairness-in-machine-learning-for-international-development-spring-2020

Full Transcript

MIT RES.EC-001 Exploring Fairness in Machine Learning, Spring 2020 Instructor: Mike Teodorescu View the complete course: https://ocw.mit.edu/RES-EC-001S20 YouTube Playlist: https://www.youtube.com/playlist?list=PLUl4u3cNGP63IFQn8FklBOUhYVcmaxpOX This video presents the confusion matrix, including true negatives, true positives, false negatives, and false positives. It discusses how to choose between different fairness criteria such as demographic parity, equalized odds, and equalized opportunity. License: Creative Commons BY-NC-SA More information at https://ocw.mit.edu/terms More courses at https://ocw.mit.edu Support OCW at http://ow.ly/a1If50zVRlQ We encourage constructive comments and discussion on OCW’s YouTube and other social media channels. Personal attacks, hate speech, trolling, and inappropriate comments are not allowed and may be removed. More details at https://ocw.mit.edu/comments.