Comment on A.I. groks 66%-76% faster with data augmentation strategies.

• Hackworth@lemmy.world ⁨2⁩ ⁨months⁩ ago

  We follow the classic experimental paradigm reported in Power et al. (2022) for analyzing “grokking”, a poorly understood phenomenon in which validation accuracy dramatically improves long after the train loss saturates. Unlike the previous templates, this one is more amenable to open-ended empirical analysis (e.g. what conditions grokking occurs) rather than just trying to improve performance metrics

  source

  • catloaf@lemm.ee ⁨2⁩ ⁨months⁩ ago

    Oh okay so they’re just redefining words that are already well-defined so they can make fancy claims.

    source

    • Hackworth@lemmy.world ⁨2⁩ ⁨months⁩ ago

      Well-defined for casual use is very different than well-defined for scholarly research. It’s standard practice to take colloquial vocab and more narrowly define it for use within a scientific discipline. Sometimes different disciplines will narrowly define the same word two different ways, which makes interdisciplinary communication pretty funny.

      source

      • technocrit@lemmy.dbzer0.com ⁨2⁩ ⁨months⁩ ago

        It’s standard practice to take colloquial vocab and more narrowly define it for use within a scientific discipline.

        No. It’s not standard at all, especially when the goal is overtly misleading.

        Sometimes different disciplines will narrowly define the same word two different ways

        Maybe one or both disciplines is promoting bullshit.

        source

        • -> View More Comments
      • Blueberrydreamer@lemmynsfw.com ⁨2⁩ ⁨months⁩ ago

        Yeah slapping a wildly misleading literary reference that completely misuses the concept into a paper is not really standard practice. At least they gave it a different spelling so as to try to differentiate, it’s a shame that it wasn’t carried over to the title.

        source