When Models Manipulate Manifolds: The Geometry of a Counting Task

Re:When Models Manipulate Manifolds: The Geometry of a Count... by lccerina on Wednesday November 05, 2025 @04:06AM (#45820938)

Still designed by humans. The loss function, backpropagation and all other mechanisms didn't just appear magically in the neural network. Someone decided which loss function to use, which architecture or which optimization techniques. Only because it takes a big GPU a lot of number crunching to assign those weights, it doesn't mean it's biological.

In the same way, a weather forecast model using a lot of complicated differential equations is not biological. A finite element model analyzing some complicated electromagnetic field, or the aerodynamics of a car is not biological. Just because someone around 70-75 years ago called them 'perceptrons' or 'neurons' instead of thingamajigs does not make them biology.

[ Parent | on HN ]

Re:When Models Manipulate Manifolds: The Geometry of a Count... by UltraSane on Wednesday November 05, 2025 @05:02AM (#45821271)

"Still designed by humans." No they are not. They are learned via backpropagation. This is the entire reason why neural networks work so well and why we have no idea how they work when they get big.

[ Parent | on HN ]

Re:When Models Manipulate Manifolds: The Geometry of a Count... by lccerina on Friday November 07, 2025 @09:15AM (#45846618)

And who designed backpropagation? It is not a magical property of artificial neurons or some law of nature or god's miracle. A bunch of mathematicians banged their head on the problem of backpropagation, tossed it to a computer, and voilà , neural networks made sense. Neural networks work so well because someone chooses the right loss function for the right problem. Wrong loss function -> wrong results. It's not magic. Nor it's biology.

[ Parent | on HN ]