• @marcos
      link
      528 months ago

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

      Overfitting alone can’t get you to 1.

      • Victor
        link
        108 months ago

        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.

        • @marcos
          link
          198 months ago

          Yes.

          You train it on some data, and ask it about different data. Otherwise it just hard-codes the answers.

        • @ArtVandelay
          link
          English
          38 months ago

          Yes, it’s called a train test split, and is often 80/20 or there about