ConceptAI & ML
Data poisoning
A failure mode where evaluation datasets or training methods are artificially constructed to be IID in a way that does not represent real-world deployment.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
2Each in their own terms, from the easiest level.
Ashwinee Panda
Inserting a crafted canary into a target data point and isolating the loss signal to force the model to memorize the canary without affecting overall performance.
Lectures that assume it
1Connections
5The lectures that define it or assume it, and the concepts next to it.