Comment on no one can understand AI

LouNeko@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

• Gladaed@feddit.org ⁨3⁩ ⁨weeks⁩ ago

  Max(input*weights, 0) is an if in a sense, I guess.

  source

  • mrchampion@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

    Good old ReLU. I’ve heard that CNN’s perform better when using ReLU as the activation func, and that’s probably why; ReLU acts as a filter on the image’s features.

    source

    • Gladaed@feddit.org ⁨3⁩ ⁨weeks⁩ ago

      Nah. Without a nonlinearity you just get a linear combination of inputs instead of the output of a deep neural network. ReLU or Ramp is just the simplest possible non linearity. Using a simple function can enable using deeper networks yielding even better performance.

      It’s actually somewhat of a headache, numerically. Works well enough tho.

      source
• Epzillon@lemmy.world ⁨3⁩ ⁨weeks⁩ ago

  Yes, it is inherently incorrect, I just think that increases the fun factor. It reminds me of that guy who wrote a prime-checker for his thesis and it was just a massive list of if-statement

  source

  • weps@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

    98% accurate prime checker, super fast

    isPrime() return False;

    source
  • Rhaedas@fedia.io ⁨3⁩ ⁨weeks⁩ ago

    A transistor is on or off. It's all if-then.

    source

    • Viceversa@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

      No, it’s all ands , ors and nots

      source

      • nop@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

        Boolean math let’s you convert it all to nand gates. For ease of manufacturing this is what is done.

        source
• glibg10b@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

  Matrix multiplication, activation functions and softmax. Also some matrix addition sometimes. That’s literally it

  source

  • Viceversa@lemmy.world ⁨2⁩ ⁨weeks⁩ ago

    Everything is quantum field fluctuations.
    That’s literally it.

    source