LFD Book Forum

LFD Book Forum (http://book.caltech.edu/bookforum/index.php)
-   The Final (http://book.caltech.edu/bookforum/forumdisplay.php?f=138)
-   -   Q12 - SVMs (http://book.caltech.edu/bookforum/showthread.php?t=4324)

Michael Reach 05-30-2013 01:45 PM

Q12 - SVMs
 
I've started working on the SVM part of the final. As I was browsing around online, I came across a piece of terminology that wasn't used in the lectures AFAIK, and I wondered what it meant.
The final asks, "The number of support vectors you get..."
But in various places I see descriptions of two types of support vectors: number of support vectors, and number of bounded support vectors. Does anyone know what is the difference between them, and which are the ones to count?

yaser 05-30-2013 03:08 PM

Re: Q13 - SVMs
 
Quote:

Originally Posted by Michael Reach (Post 10993)
I've started working on the SVM part of the final. As I was browsing around online, I came across a piece of terminology that wasn't used in the lectures AFAIK, and I wondered what it meant.
The final asks, "The number of support vectors you get..."
But in various places I see descriptions of two types of support vectors: number of support vectors, and number of bounded support vectors. Does anyone know what is the difference between them, and which are the ones to count?

In this case, we are using hard-margin SVM and therefore there is only one type of support vectors (achieving the margin exactly). The different types arise in soft-margin SVM because some support vectors there violate the margin.


All times are GMT -7. The time now is 05:49 AM.

Powered by vBulletin® Version 3.8.3
Copyright ©2000 - 2020, Jelsoft Enterprises Ltd.
The contents of this forum are to be used ONLY by readers of the Learning From Data book by Yaser S. Abu-Mostafa, Malik Magdon-Ismail, and Hsuan-Tien Lin, and participants in the Learning From Data MOOC by Yaser S. Abu-Mostafa. No part of these contents is to be communicated or made accessible to ANY other person or entity.