underaxon·5 年前·議論I may be wrong but I think this is what kernel methods (eg. SVM) do, right? So this looks like a (deep)SVM where the kernels are small NNs.
underaxon·6 年前·議論I've made some experiments that you can check out here:http://www.clungu.com/Distilling_a_Random_Forest_with_a_sing...