• @RandomVideos@programming.dev
    link
    fedilink
    English
    12 months ago

    By analyzing, isnt it awarding points based on how well you can replicate it and redoing it in an attempt to obtain more points?

    • FaceDeer
      link
      fedilink
      12 months ago

      Very basically, yes. But the result is a model that doesn’t actually contain the training data, it’s too small for it to be physically possible.