Why you should care about debugging machine learning models
O'Reilly Media - Data
DECEMBER 12, 2019
For all the excitement about machine learning (ML), there are serious impediments to its widespread adoption. 8] Data about individuals can be decoded from ML models long after they’ve trained on that data (through what’s known as inversion or extraction attacks, for example). ML security audits. Discrimination remediation.
Let's personalize your content