Thread: Q9, SVM vs PLA
View Single Post
  #11  
Old 05-23-2013, 03:28 AM
catherine catherine is offline
Member
 
Join Date: Apr 2013
Posts: 18
Default Re: Q9, SVM vs PLA

@jlaurentum:
These are the parameters I fed to ipop:
Code:
H = sweep(XIn[,2:3],MARGIN=1,yIn, '*')
c = matrix(rep(-1,n))
A = t(yIn)
b = 0
l = matrix(rep(0,n))
u = matrix(rep(1e7,n))
r = 0
sv = ipop(c,H,A,b,l,u,r)
I'm not sure why but I had to tweak u to get a 0 Ein across the board, ie for all 1,000 iterations. I have to admit that the technicalities of quadratic programming go a tad over my head :/

Last edited by catherine; 05-23-2013 at 03:32 AM. Reason: more details
Reply With Quote