News for hackers. Stuff that matters.

A comment on Gradient Boosting Explained in 3D. Parent comment

Re:Gradient Boosting Explained in 3D by romaniv on Wednesday July 27, 2016 @04:27PM (#12176240)
Can wavelet decompose be trained for classification of feature vectors with many dimensions?
[ Parent | on HN ]
Re:Gradient Boosting Explained in 3D by enthdegree on Wednesday July 27, 2016 @04:41PM (#12176355)
Yes that is what they are for. In this case you probably don't even really need wavelets and you can just use a Fourier transform
[ Parent | on HN ]
Re:Gradient Boosting Explained in 3D by romaniv on Thursday July 28, 2016 @09:42AM (#12180108)
Fourier transform is not a classification mechanism. You can transform something into frequency domain, but that doesn't inform you which frequencies are most relevant in classifying samples.
[ Parent | on HN ]