[Der_Einzige]

You didn't explain why its faster though.

It's faster because its reduces the dimensionality of the inputs down to something manageable (hundreds or low thousands). You can replace convolutions with most other types of dimensionality reduction (including other types of layers) and outside of image tasks you'll get very similar or even better performance.

[elcritch]

I wonder if that’d work by doing a 2d Fourier transformer on an image before hand, but you’re not reducing dimensionally that way.