Group Theory and Machine Learning

author: Risi Kondor, London's Global University
published: March 3, 2008,   recorded: October 2007,   views: 35312


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.


Machine Learning Tutorial Lecture The use of algebraic methods—specifically group theory, representation theory, and even some concepts from algebraic geometry—is an emerging new direction in machine learning. The purpose of this tutorial is to give an entertaining but informative introduction to the background to these developments and sketch some of the many possible applications, including multi-object tracking, learning rankings, and constructing translation and rotation invariant features for image recognition. The tutorial is intended to be palatable by a non-specialist audience with no prior background in abstract algebra.

See Also:

Download slides icon Download slides: mlcued08_kondor_gtm.pdf (2.4 MB)

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 Hassan, July 10, 2008 at 9:46 p.m.:

I think you definitely need to know some group theory before you see this, as well as some harmonic analysis. The ideas are very interesting, but difficult, especially for a machine learning researcher with the usual background in mainly statistics and linear algebra.

Comment2 iniciar sesion en gmail, January 2, 2019 at 8:19 a.m.:


Comment3 davidgalli, June 1, 2019 at 11:47 a.m.:

AI, huge information, distributed computing, and AI all bind together to something very similar: information driven comprehension of an enormous point. These themes are advertised each in light of the fact that they play into the environment that encourages us anticipate and break down an enormous scale issue that doesn't have an unmistakably characterized answer <a href=""></a>

Comment4 ghdsports, June 30, 2019 at 1:18 p.m.:

i Love to learn machine learning course and thank you for your wonderful info -

Comment6 jika, March 28, 2020 at 5:16 a.m.:

A very meaningful event, I hope everything will go well

Comment8 BenStill, April 7, 2020 at 11:14 a.m.:


Comment9 Joy Anthony, June 15, 2020 at 10:36 a.m.:

Thanks to the site for the info:

Comment10 Allen, June 15, 2020 at 5:26 p.m.:

I like this topic because I am always interested in computer algorithms.

Comment11 vebako, October 12, 2020 at 10:24 a.m.:

The process of seeking an appointment with doctors and making online payments at paymydoctor is quite simple and easy.

Write your own review or comment:

make sure you have javascript enabled or clear this field: