![Avatar](/_next/image?url=%2Flemmy-icon-96x96.webp&w=3840&q=75)
Parent [none/use name]
I was just wondering today if anyone has used Chatgpt to try to translate Hagel into modern vernacular.
Is it possible someone off camera called his attention and asked something? Maybe that’s why he gives the thumbs up? Idk that’s the only other explanation I can think of.
Well, addition is built into the instruction set of any CPU, so it only takes one operation. On the other hand, one evaluation of a neural net involves several repeated matrix-vector multiplies followed by the application of a nonlinear “activation function”. Matrix-vector multiply for a square matrix will take 2020=400 multiply operations and about 2019 addition operations for a 20-dimensional input. So we’ll say maybe on the order of 1,000-10,000 times more operations depending on how many layers?