-
A Note on Deep Scattering Spectrum
This note covers deep scattering spectrum (Mallat, 2012), a feature extraction technique for processing of speech signals and images. The scattering transform is given by a cascade of wavelet transforms and modulus non-linearity. It generates features of different orders, with the first order coefficients approximately equal to the Mel-frequency cepstrum, and higher order coefficients recovering information lost at lower levels of the cascade.
-
a post with comments
an example of a blog post with comments
-
a post with code
an example of a blog post with some code
-
a post with images
this is what included images could look like
-
a post with formatting and links
march & april, looking forward to summer