• marcos@lemmy.world
    2 years

    Your neural network just learned to flawlessly answer any question you send it! Time to put it to good use!

    Start asking the important questions!

    • marcos@lemmy.world
      2 years

      No, this is because the testing set can be derived from the training set.

      Overfitting alone can’t get you to 1.

      • Victor@lemmy.world
        2 years

        So as an eli5, that’s basically that you have to “ask” it stuff it has never heard before? AI has come after my time in higher education.

      • sevenapples@lemmygrad.ml
        2 years

        It can if you don’t do a train-test split.

        But even if you consider the training set only, having zero loss is definitely a bad sign.

  • gerryflap@feddit.nl
    2 years

    I like how specifically this relates to my experience with the discount factor gamma in Reinforcement Learning. Like, pretty close to the exact numbers (though missing 0.99 and 0.999)