Rank: 3265 based on 38 downloads (last 30 days) and 1 file submitted
photo

Kai

E-mail
Company/University
LBL

Personal Profile:
Professional Interests:

 

Watch this Author's files

 

Files Posted by Kai
Updated   File Tags Downloads
(last 30 days)
Comments Rating
01 Oct 2012 Screenshot Improved Nystrom Kernel Low-rank Approximation efficient, self-complete implementation of improved Nystrom low-rank approximation Author: Kai machine learning, matrix lowrank approx..., manifold learning and... 38 1
  • 5.0
5.0 | 1 rating
Comments and Ratings on Kai's Files
Updated File Comment by Comments Rating
10 Dec 2012 Improved Nystrom Kernel Low-rank Approximation efficient, self-complete implementation of improved Nystrom low-rank approximation Author: Kai Henriques, Joao

Works as advertised! To train a linear SVM in the Nystrom feature-space, replace the computation of G and Ktilde at the end of INys() with:

M = Ve(:,pidx) * inVa;
Mdata = E * M;

then train SVM with Mdata (which has all training samples in the new feature space). To compute the same features for a test vector z, use:

Mz = exp(-sqdist(z', center')/kernel.para) * M;

and classify with the same linear SVM.

Contact us