Wavelet scattering is a convolutional network formed by cascade of wavelets, modulus nonlinearities, and lowpass filters. It yields invariant, sparse, and stable representations useful for classification, generation, and other tasks. Filters are fixed, but architecture differentiable and extendable with learned layers adapted to data.

There is no tag wiki for this tag … yet!

Tag wikis help introduce newcomers to the tag. They contain an overview of the topic defined by the tag, along with guidelines on its usage.

All registered users may propose new tag wikis.

(Note that if you have less than 20000 reputation, your tag wiki will be peer reviewed before it is published.)