Fairness in Machine Learning with Hanna Wallach

Today we’re joined by Hanna Wallach, a Principal Researcher at Microsoft Research.

Subscribe: iTunes / Google Play / Spotify / RSS

Hanna and I really dig into how bias and a lack of interpretability and transparency show up across machine learning. We discuss the role that human biases, even those that are inadvertent, play in tainting data, and whether deployment of “fair” ML models can actually be achieved in practice, and much more. Along the way, Hanna points us to a TON of papers and resources to further explore the topic of fairness in ML. You’ll definitely want to check out the notes page for this episode, which you’ll find at twimlai.com/talk/232.

Get the transcript

Thanks to our Sponsor!

We’d like to thank Microsoft for their support and their sponsorship of this series. Microsoft is committed to ensuring the responsible development and use of AI and is empowering people around the world with intelligent technology to help solve previously intractable societal challenges spanning sustainability, accessibility and humanitarian action. Learn more at Microsoft.ai

About Hanna

• Hanna on Twitter
• Hanna at Microsoft
• Hanna’s Personal Page
• Register here for Microsoft Research’s on Demand Webinar: Machine Learning and Fairness Hosted by Hanna Wallach

Mentioned in the Interview

• Paper: Gender Shades: Intersectional Accuracy Disparities in Commercial Gender Classification
• Story: Amazon scraps secret AI recruiting tool that showed bias against women
• ProPublica: Machine Bias
• Paper: Discrimination in Online Ad Delivery
• Paper: Semantics derived automatically from language corpora contain human-like biases
• Paper: Distributed Representations of Words and Phrases and their Compositionality
• Paper: Unequal Representation and Gender Stereotypes in Image Search Results for Occupations
• Jenn Wortman Vaughn – Tutorial: Challenges of incorporating algorithmic fairness into industry practice
• Paper: A Reductions Approach to Fair Classification
• Paper: Improving fairness in machine learning systems: What do industry practitioners need?
• ACM Conference on Fairness, Accountability, and Transparency ACM FAT*)
• AI Now Institute
• danah boyd
• Partnership on AI

• Follow along with the AI for the Benefit of Society series!

• Download our AI Platforms eBook Series!
• Check out all of our great series from 2018 at the TWIML Presents: Series page!
• TWIML Online Meetup
• Register for the TWIML Newsletter

“More On That Later” by Lee Rosevere licensed under CC By 4.0