Go offline with the Player FM app!
156 | Visualizing Fairness in Machine Learning with Yongsu Ahn and Alex Cabrera
Manage episode 255289367 series 32120
In this episode we have PhD students Yongsu Ahn and Alex Cabrera to talk about two separate data visualization systems they developed to help people analyze machine learning models in terms of potential biases they may have. The systems are called FairSight and FairVis and have slightly different goals. FairSight focuses on models that generate rankings (e.g., in school admissions) and FairVis more on comparison of fairness metrics. With them we explore the world of “machine bias” trying to understand what it is and how visualization can play a role in its detection and mitigation.
[Our podcast is fully listener-supported. That’s why you don’t have to listen to ads! Please consider becoming a supporter on Patreon or sending us a one-time donation through Paypal. And thank you!]
Enjoy the show!
Links:
- Alex Cabrera
- Yongsu Ahn
- FairSight
- FairVis
- Google: “Attacking Discrimination with Smarter Machine Learning”
- Nicky Case: “Parable of Polygons”
Related episodes
Chapters
1. Welcome to Data Stories! (00:00:33)
2. Our podcast is listener-supported, please consider making a donation (00:01:07)
3. Our topic today: Bias and fairness in machine learning (00:01:41)
4. Our guests: Alex Cabrera (00:02:48)
5. and Yongsu Ahn (00:03:14)
6. How to define 'fairness' and 'bias' in machine learning? (00:03:54)
7. Examples of discriminitation in machine learning (00:08:49)
8. What is FairSight? (00:13:22)
9. What is FairVis? (00:17:00)
10. Do you have advice on how to get started with the topic? (00:38:32)
11. Get in touch with us and support us on Patreon (00:52:10)
173 episodes
Manage episode 255289367 series 32120
In this episode we have PhD students Yongsu Ahn and Alex Cabrera to talk about two separate data visualization systems they developed to help people analyze machine learning models in terms of potential biases they may have. The systems are called FairSight and FairVis and have slightly different goals. FairSight focuses on models that generate rankings (e.g., in school admissions) and FairVis more on comparison of fairness metrics. With them we explore the world of “machine bias” trying to understand what it is and how visualization can play a role in its detection and mitigation.
[Our podcast is fully listener-supported. That’s why you don’t have to listen to ads! Please consider becoming a supporter on Patreon or sending us a one-time donation through Paypal. And thank you!]
Enjoy the show!
Links:
- Alex Cabrera
- Yongsu Ahn
- FairSight
- FairVis
- Google: “Attacking Discrimination with Smarter Machine Learning”
- Nicky Case: “Parable of Polygons”
Related episodes
Chapters
1. Welcome to Data Stories! (00:00:33)
2. Our podcast is listener-supported, please consider making a donation (00:01:07)
3. Our topic today: Bias and fairness in machine learning (00:01:41)
4. Our guests: Alex Cabrera (00:02:48)
5. and Yongsu Ahn (00:03:14)
6. How to define 'fairness' and 'bias' in machine learning? (00:03:54)
7. Examples of discriminitation in machine learning (00:08:49)
8. What is FairSight? (00:13:22)
9. What is FairVis? (00:17:00)
10. Do you have advice on how to get started with the topic? (00:38:32)
11. Get in touch with us and support us on Patreon (00:52:10)
173 episodes
All episodes
×Welcome to Player FM!
Player FM is scanning the web for high-quality podcasts for you to enjoy right now. It's the best podcast app and works on Android, iPhone, and the web. Signup to sync subscriptions across devices.