SMO is sequential minimal optimization. It is a way to train SVMs that is very easy to program since it doesn't need a general quadratic optimization program. You can find the pseudocode in the book Introduction to Support Vector Machines by Cristianini or in Platt's papers:
J. Platt. "How to implement SVMs," IEEE Intelligent Systems, July/August 1998.
J. Platt. "Fast training of support vector machines using sequential minimal optimization," Advances in Kernel Methods * Support Vector Learning, Edited by B. Scholkopf, C Gurges, and A. Smola, The MIT Press, pp. 185-208, 1999.
>>> [log in to unmask] 7/9/2004 2:25:50 PM >>>
What is SMO ? Any link or ref on this ?
Thanks
Chang Hsiung
Smiths Detection
-----Original Message-----
From: Christophe Guéret [mailto:[log in to unmask]]
Sent: Friday, July 09, 2004 11:07 AM
To: [log in to unmask]
Subject: Re: Optimal weight vector
You should have a look on the "SMO" algorithm
Le ven 09/07/2004 à 19:23, Shwetha Harish a écrit :
Hi !
I am trying to use SVM for spam filtering.
I have categorized a bunch of emails into spam and non-spam and I have y =
{-1,+1} and alos xi.
I am unable to understand as to how to calcalute the optimal weight vector
and the constant b.
I am trying to formula yi(w.xi-b)>=1
Could you please help me.
Thanks in advance
Shwetha Harish
|