Model inspection and interpretation at Seldon (Practical AI #48)

Interpreting complicated models is a hot topic. How can we trust and manage AI models that we can’t explain? In this episode, Janis Klaise, a data scientist with Seldon, joins us to talk about model interpretation and Seldon’s new open source project called Alibi. Janis also gives some of his thoughts on production ML/AI and how Seldon addresses related problems.

Join the discussion

Changelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!

Sponsors:

• DigitalOcean – Check out DigitalOcean’s dedicated vCPU Droplets with dedicated vCPU threads. Get started for free with a $50 credit. Learn more at do.co/changelog.
• DataEngPodcast – A podcast about data engineering and modern data infrastructure.
• Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com.

Featuring:

• Janis Klaise – GitHub, LinkedIn, X
• Chris Benson – Website, GitHub, LinkedIn, Bluesky, X
• Daniel Whitenack – Website, GitHub, X

Show Notes:

• Seldon
• Seldon Core
• Alibi

Books

• “The Foundation Series” by Isaac Asimov
• “Interpretable Machine Learning” by Christoph Molnar

Something missing or broken? PRs welcome!