DevConf.CZ 2019 has ended
Back To Schedule
Sunday, January 27 • 9:30am - 10:20am
Using Machine Learning to find Linux bugs

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

Feedback form is now closed.
I’d like to show you how to find bugs in Linux systems using machine learning, when paired with the totally seemingly useless and annoying false positives that come out of your integration tests.

We’ve all been frustrated unreproducible bugs in Linux … And also by stupid test-flakes that show up as failures in integration tests even though nothing related has changed. I want to prove that both of these are the same thing.

Lets take a look at how the Cockpit project trains bots to correlate these flakes into unsupervised clusters. and automatically make use of the data, identifying real bugs, or simply retriggering tests.

We’ll dive into details about Normalized Compression Distance, Unsupervised Clustering, TF-IDF and many other simple techniques used to zero in on the bugs.

avatar for Stef Walter

Stef Walter

Hacker, manager, and CI freak., Red Hat
Stef is an avid open source hacker. He's contributed to over a hundred open source projects, and can be found preaching about continuous integration and working on the Cockpit Linux admin interface. He's a usability freak. Stef lives in Germany, and works at Red Hat.

Sunday January 27, 2019 9:30am - 10:20am CET