Re:The Fourier transform is a neural network
by akrymski on Thursday April 29, 2021 @11:20AM
(#26982313)
I don't see why processing JPEG coefficients directly as input features shouldn't have similar accuracy to a much larger NN using raw pixel data.
In particular I'm interested in the efficiency gains from avoiding convolutions and the possibility of running a compressed frequency-domain NN on CPUs.
In particular I'm interested in the efficiency gains from avoiding convolutions and the possibility of running a compressed frequency-domain NN on CPUs.