Support Vector Machines

author: Chih-Jen Lin, Department of Computer Science and Information Engineering, National Taiwan University
published: Feb. 25, 2007,   recorded: July 2006,   views: 165422


Related Open Educational Resources

Related content

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.
Lecture popularity: You need to login to cast your vote.

 Watch videos:   (click on thumbnail to launch)

Watch Part 1
Part 1 1:17:15
Watch Part 2
Part 2 1:16:37
Watch Part 3
Part 3 1:20:39


Support vector machines (SVM) and kernel methods are important machine learning techniques. In this short course, we will introduce their basic concepts. We then focus on the training and optimization procedures of SVM. Examples demonstrating the practical use of SVM will also be discussed. Basically we focus on classification. If time is allowed, we will also touch SVM regression.

See Also:

Download slides icon Download slides: mlss06tw_lin_svm.pdf (1.1┬áMB)

Help icon Streaming Video Help

Link this page

Would you like to put a link to this lecture on your homepage?
Go ahead! Copy the HTML snippet !

Reviews and comments:

Comment1 ben, May 14, 2007 at 1:07 p.m.:

I like it.

Comment2 Thorsten Pfister, May 15, 2007 at 12:27 a.m.:

Excellent explanation of concepts and issues. Thank you!

Comment3 peerasak, July 16, 2007 at 5:59 a.m.:

It is a very nice lecture.

Comment4 Giorgio, September 25, 2007 at 9:35 p.m.:

Bizarre typo up there... If they are NOT important, why teach them? :)

"Support vector machines (SVM) and kernel methods are not important machine learning techniques"

Comment5 peter (staff), November 27, 2007 at 6:55 p.m.:

Giorgio... Thanks, I've fixed the typo.

Comment6 roywwcheng, November 28, 2007 at 6:09 p.m.:

As one core developer of LIBSVM, Lin has introduced full and accurate practical issues of SVM in this talk.

Thanks a lot.

Comment7 yong kassian, January 20, 2008 at 8:19 a.m.:

As a core Machine learning tool Lin has introduce a full and practical lectures in his talk on the SVM . I like it

Comment8 sss, April 7, 2008 at 3:21 a.m.:

nice talk,
it is really good

Comment9 tucooooo, June 19, 2008 at 8:22 p.m.:

really great ! it s always better to ear explanations than reading a short paper...
Thank you.

Comment10 mrg, June 27, 2008 at 11:44 a.m.:

Very hard to understand, not very structured and poor articulation... The lecture of Colin Campbell on SVM is way better!

Still, thanks for having these videos available!

Comment11 eleph, October 7, 2008 at 12:30 p.m.:

it is very good.I need this right now.typical Chinese accent.
thanks a lot!!!

Comment12 Phil, December 30, 2008 at 4:18 a.m.:

How can I download the file?
I want to get just the audio.

Comment13 Rohan, February 1, 2009 at 9:26 a.m.:

amazing lecture,
he has introduced svm's in an awesome manner , also he has pointed out areas of further research and also on how to practically train a svm classifier.

Thank you!!

Comment14 Ayman, May 20, 2009 at 5:20 p.m.:


I want to download the lecture (Video+audio), How?

Thank you,

Comment15 raja, September 25, 2009 at 10:04 a.m.:

how can i download your lecture, is it possible?

Comment16 karim, September 29, 2009 at 6:32 a.m.:

I can not watch this video if you like it helps me and send me this video i need him soo much

Comment17 hb, November 8, 2009 at 1:35 a.m.:

the best explaination on SVM so far.
all the books and papers seem so poorly written compared to this lecture :-)

Comment18 arezoo, March 14, 2010 at 8:59 p.m.:

hi.i want to know about svm and rbf it ok to send me some pdf about them.

Comment19 Tergino, April 23, 2010 at 9:07 p.m.:

This lecture was so helpful, I really love this website and think that it is an excellent learning tool

Comment20 Truong Xuan Tung, September 10, 2010 at 2:01 p.m.:

this is nice lecture.
thank you so much.

Comment21 Patrick St, October 12, 2010 at 1:18 a.m.:

Nice lecture and easy to understand...

Comment22 Krishna Chaitanya, December 15, 2010 at 12:04 p.m.:

Very nice lecture, initially i overlooked this video after just checking the pronunciation...but best so far.

Comment23 unknown, April 1, 2011 at 4:20 p.m.:

please tell me how can i download the videos?
thank you

Comment24 luyendt, July 23, 2011 at 5:24 a.m.:

I like it.
However my English is not good, so i can't listen to this video in some word. :(
Anyway, thank you so much!

Comment25 luyendt, July 23, 2011 at 5:24 a.m.:

I like it.
However my English is not good, so i can't listen to this video in some word. :(
Anyway, thank you so much!

Comment26 Sivagaminathan, November 5, 2011 at 3:41 p.m.:

Excellent Lecture.....
A new concept widely used nowadays in machine learning.
It is obviously used for classification and ranking.

Wonderful presentation!
Thanks a lot!


Comment27 Sivagaminathan, November 5, 2011 at 3:47 p.m.:

Please give me softcopy of power point files,
i need videlectures of SVM...

I have to use this SVM model for clustering and ranking
in my IR research task..

Iam requesting author to extend your help!!!

Thanks and Regards,

Comment28 chairly, December 8, 2011 at 2:38 p.m.:

It is a very nice lecture. Thank you very much.

Comment29 AFei, December 24, 2011 at 3:11 p.m.:

The video is good. But I really need to download it the live stream is too slow, I can't finish it smoothly.

Comment30 Yu Zheng, May 12, 2012 at 5:08 p.m.:

Excellent!! very useful information for practical application of SVM.

Comment31 Tarik Rashid, January 28, 2013 at 9:25 p.m.:

Could you please send me the video?
Thanks and regards

Comment32 teerachat saeheng, May 27, 2014 at 3:48 a.m.:

thanks , this video is so nice but the third part is invalid now.

Comment33 denis, August 8, 2018 at 6:44 a.m.:

In SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall.

Comment34 bokilo, June 20, 2022 at 6:29 a.m.:

This is so amazing, great minds think alike I just wrote a similar post on this topic! You should check it out.

Write your own review or comment:

make sure you have javascript enabled or clear this field: