In machine learning (in particular, supervised learning), if some new data changes the previous model/function drastically, then I think we should study that data. Does it happen? How to handle such a situation?

  • 1
    $\begingroup$ Welcome to AI! I've taken the liberty of adding the "ai-basics" and "models" tag. $\endgroup$
    – DukeZhou
    May 11 '18 at 13:17
  • $\begingroup$ I'd guess the new data has a different distribution then what the model has seen up to that point. So, distribution shift would be the first thing that'd come to my mind. $\endgroup$
    – SpiderRico
    Oct 28 '21 at 20:55

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.