Real World Model Explainability with Rayid Ghani

800 800 The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

Today we’re joined by Rayid Ghani, Director of the Center for Data Science and Public Policy at the University of Chicago.

Rayid’s goal is to combine his skills in machine learning and data with his desire to improve public policy and the social sector. Drawing on his range of experience from the corporate world to Chief Scientist for the 2012 Obama Campaign, Rayid saw that while automated predictions can be helpful, they don’t always paint a full picture. The key is the context and details required when making tough decisions involving humans and their lives. In our conversation, we delve into the world of explainability methods, including the necessary human involvement, machine feedback loop and how he is working to effectively solve problems in the world today.

About Rayid

From the Interview

TWIMLcon Update

If you love this podcast, you definitely don’t want to miss the very first TWIMLcon, which is coming up soon. The two day conference will focus on topics like:

  • Overcoming the barriers to getting machine learning and deep learning models into production
  • How to apply MLOps and DevOps to the machine learning workflow in your enterprise
  • The latest approaches to platform technologies for accelerating and scaling machine learning and deep learning in the enterprise
  • Experiences and lessons-learned in delivering platform and infrastructure support for data management, experiment management, and model deployment
  • Platform deployment stories from leading companies like Google, Facebook, Airbnb, and more
  • Organizational and cultural best practices for success

Register today at If you’ve got a great story to tell in this area, there’s still time to submit a proposal for our Call for Presenters, which has been extended until July 19th. Accepted talks will be notified no later than August 15th. Head over to to submit your presentation!

Meetup Update!

Many of you are aware that we’ve been hosting a couple of paper-reading meetups in conjunction with the podcast. I’m excited to share that Matt Kenney, Duke staff researcher and long-time listener and friend of the show, has stepped up to help take this group to the next level. The paper reading meetup will now be meeting every other Sunday at 1 PM Eastern Time to dissect the latest and greatest academic research papers in ML and AI. If you want to take your understanding of the field to the next level, please join us on Sunday, July 28th, or check for more upcoming community events.

We’ve also got a couple of study groups currently running, one working through the Deep Learning from the Foundations course, another on [Natural Language Processing] (, and another working through the Stanford cs224n Deep Learning for Natural Language Processing course. These study groups just started and will be working on these courses through October and November, so it’s not too late to join. Sign up on the meetup page at

Check it out

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

1 comment

Leave a Reply

Your email address will not be published.