Thursday 10:45–11:30 in Main Track, Track 2, Track 3

Trusted AI – Building Reproducible, Unbiased and Robust AI Pipelines using the python OpenSource sta

Romeo Kienzler

Audience level:
Novice

Description

Untrusted AI doesn’t make it into production. The concerns are just too high. In this talk we’ll show how data lineage, bias detection, adversarial robustness and model explainability can be achieved using an open source stack

Abstract

Untrusted AI doesn’t make it into production. The concerns are just too high. In this talk we’ll show how data lineage, bias detection, adversarial robustness and model explainability can be achieved using an open source stack

Subscribe to Receive PyData Updates

Subscribe