Re:Understanding Neural Networks Through Deep Visualization
by mjw on Thursday July 09, 2015 @04:47AM
(#9856797)
When you penalise the L2 norm of the convolution of the image with a filter (like a gradient or edge detector for example) you are effectively doing this. The spectrum of the filter determines how much different frequency components are penalised.
I think (although they're a little handwavey about it) that their "Gaussian blur" prior must be of this form. They certainly talk about it penalising high frequency components.
The total variation method they mention is a generalisation of this too.
See https://en.wikipedia.org/wiki/Tikhonov_regularization
https://en.wikipedia.org/wiki/Regularization_by_spectral_fil...
I think (although they're a little handwavey about it) that their "Gaussian blur" prior must be of this form. They certainly talk about it penalising high frequency components.
The total variation method they mention is a generalisation of this too.