The data I'm using is a set of images from 10 different categories. For the training data I have label values that tell me which image belongs in which category. I am trying to reduce the dimensionality to 2 dimensions and estimate label values of the dimension reduced testing data. To do this I'm using KSPCA with various kernels, but I'm stuck trying to figure out how to estimate the labels (which category each image fits in) for the testing set.

Just to add some more info, I'm using the following algorithm:

KSPCA Alg

asked Dec 13 '14 at 18:57

JohnnyBravo's gravatar image

JohnnyBravo
1112

edited Dec 13 '14 at 19:00

Be the first one to answer this question!
toggle preview

powered by OSQA

User submitted content is under Creative Commons: Attribution - Share Alike; Other things copyright (C) 2010, MetaOptimize LLC.