• Socsa@sh.itjust.works
    link
    fedilink
    English
    arrow-up
    57
    arrow-down
    4
    ·
    10 days ago

    Bayesian purist cope and seeth.

    Most machine learning is closer to universal function approximation via autodifferentiation. Backpropagation just lets you create numerical models with insane parameter dimensionality.

      • hotsox@lemmy.blahaj.zone
        link
        fedilink
        English
        arrow-up
        23
        arrow-down
        5
        ·
        edit-2
        10 days ago

        Universal function approximation - neural networks.

        Auto-differentiation - algorithmic calculation of partial derivatives (aka gradients)

        Backpropagation - when using a neural network (or most ML algorithms actually), you find the difference between model prediction and original labels. And the difference is sent back as gradients (of the loss function)

        Parameter dimensionality - the “neurons” in the neural network, ie, the weight matrices.

        If thats your argument, its worse than Statistics imo. Atleast statistics have solid theorems and proofs (albeit in very controlled distributions). All DL has right now is a bunch of papers published most often by large tech companies which may/may not work for the problem you’re working on.

        Universal function approximation theorem is pretty dope tho. Im not saying ML isn’t interesting, some part of it is but most of it is meh. It’s fine.

  • The Snark Urge@lemmy.world
    link
    fedilink
    English
    arrow-up
    40
    arrow-down
    2
    ·
    10 days ago

    Eh. Even heat is a statistical phenomenon, at some reference frame or another. I’ve developed model-dependent apathy.

  • FaceDeer@fedia.io
    link
    fedilink
    arrow-up
    65
    arrow-down
    36
    ·
    10 days ago

    The meme would work just the same with the “machine learning” label replaced with “human cognition.”

    • wizardbeard@lemmy.dbzer0.com
      link
      fedilink
      English
      arrow-up
      84
      arrow-down
      10
      ·
      10 days ago

      Have to say that I love how this idea congealed into “popular fact” as soon as peoples paychecks started relying on massive investor buy in to LLMs.

      I have a hard time believing that anyone truly convinced that humans operate as stochastic parrots or statistical analysis engines has any significant experience interacting with others human beings.

      Less dismissively, are there any studies that actually support this concept?