If statements aren't written automatically based on training data. They are thought up by the programmer and are fixed. So not a good comparison at all unless you're talking about an AI that writes its own if statements, kind of like how the human brain changes itself.
Weights don't come from the programmer so there is plenty of room for the AI to do things the programmer didn't think of. That's the important thing. Those allow the AI not only to deal with things from a vast library of training data, but also to interpolate and extrapolate from that data.
I actually did study lambda calculus and it's nothing to do with automatically generating if statements, it's just defining functions that can take input including other functions. It doesn't involve training or creative output like you get from generative AI.
A neural network is essentially a psudoinfinite matrix of if-thens designed to vectorize information.
I like to call it recursive beer pong.
If statements aren't written automatically based on training data. They are thought up by the programmer and are fixed. So not a good comparison at all unless you're talking about an AI that writes its own if statements, kind of like how the human brain changes itself.
Weights don't come from the programmer so there is plenty of room for the AI to do things the programmer didn't think of. That's the important thing. Those allow the AI not only to deal with things from a vast library of training data, but also to interpolate and extrapolate from that data.
This is telling me you've never touched lambda, and never written an interpreter.
I actually did study lambda calculus and it's nothing to do with automatically generating if statements, it's just defining functions that can take input including other functions. It doesn't involve training or creative output like you get from generative AI.