Comment on Squiggly Boie

• idiomaddict@lemmy.world ⁨10⁩ ⁨months⁩ ago

  Thank you

  source
• HeyThisIsntTheYMCA@lemmy.world ⁨10⁩ ⁨months⁩ ago

  LLM models or ML in general? i’ve only known folk who worked on ML, not actually done it myself

  source

  • kurwa@lemmy.world ⁨10⁩ ⁨months⁩ ago

    LLMs definitely, but not all machine learning uses neural networks

    source

    • HeyThisIsntTheYMCA@lemmy.world ⁨10⁩ ⁨months⁩ ago

      ohhhh so that’s The model for neural networks, not A model for neural networks

      source

      • Tamo240@programming.dev ⁨10⁩ ⁨months⁩ ago

        Its an abstraction for neural networks. Different individual networks might vary in number of layers (columns), nodes (circles), or loss function (lines), but the concept is consistent across all.

        source

        • -> View More Comments
      • NotANumber@lemmy.dbzer0.com ⁨10⁩ ⁨months⁩ ago

        It’s only one type of neural network. A dense MLP. You have sparse neural networks, recurrent neural networks, convolutional neural networks and more!

        source
    • Aceticon@lemmy.dbzer0.com ⁨10⁩ ⁨months⁩ ago

      I haven’t really done Neural Networks in 2 decades, and was under the impression that NNs pretty much dominate Machine Learning nowadays, whilst stuff like Genetic Algorithms were way less popular or not at all used anymore.

      Is that the case?

      source

      • howrar@lemmy.ca ⁨10⁩ ⁨months⁩ ago

        Neural networks are a class of models. Genetic algorithms are a class of learning algorithms. You use learning algorithms to train models. Genetic algorithms are a valid way of training neural networks, but this is not currently in vogue. They’re typically trained via gradient descent.

        source
      • Nikls94@lemmy.world ⁨10⁩ ⁨months⁩ ago

        I don’t know if it is the case for the world today, but all those Models behave like genetic algorithms and IF-functions with a little RNG sprinkled on top of them.

        source

        • -> View More Comments
  • NotANumber@lemmy.dbzer0.com ⁨10⁩ ⁨months⁩ ago

    Not all machine learning is AI. There are plenty of Machine Learning algorithms like Random Forests that are not neural networks. Deep learning would be big neural networks.

    source

    • howrar@lemmy.ca ⁨10⁩ ⁨months⁩ ago

      Not all machine learning is AI

      The other way around. Machine learning is a subset of AI.

      source

      • NotANumber@lemmy.dbzer0.com ⁨10⁩ ⁨months⁩ ago

        You are correct. I had to actually look that up.

        source
• ghost_of_faso3@lemmygrad.ml ⁨10⁩ ⁨months⁩ ago

  just from being a dumbass and not knowing what AI shit is I thought it was a representation of the double-slit experiment i

  source