Mehrnoosh Sameki on Responsible AI
The InfoQ Podcast
00:00
How to Solve Negative Results in Your Model
Sometimes it is wow you're really under representing a certain group in your training data that's why the model never learns how to even respond for that group. Sometimes it's about augmenting data collecting more data on a completely erased population or collecting better high quality diverse data on some particular population. All of those are possible and depending on what you're diagnosing you can take the target at mitigation. It could look like 20 plus things so I just categorized a few of them for you.
Transcript
Play full episode
