https://github.com/boechat107/svm_optimization
Fundamentals of the Support Vector Machines for classification. A work for the convex optimization course of das-ufsc.
https://github.com/boechat107/svm_optimization
Last synced: 2 months ago
JSON representation
Fundamentals of the Support Vector Machines for classification. A work for the convex optimization course of das-ufsc.
- Host: GitHub
- URL: https://github.com/boechat107/svm_optimization
- Owner: boechat107
- Created: 2012-10-30T11:32:01.000Z (over 12 years ago)
- Default Branch: master
- Last Pushed: 2014-09-14T17:26:27.000Z (over 10 years ago)
- Last Synced: 2025-01-21T13:25:50.636Z (4 months ago)
- Language: TeX
- Size: 508 KB
- Stars: 1
- Watchers: 3
- Forks: 3
- Open Issues: 0
-
Metadata Files:
- Readme: Readme.md
Awesome Lists containing this project
README
# SVM optimization problem
This was a homework done for a *convex optimization* class and it's objective is to
introduce the optimization problem behind the *Support Vector Machines* for
classification tasks.
The `tex` file was used to give a presentation of the homework and it contains all
the mathematical formulation to explain the SVM optimization problem and how it is
used to be solved.
The code was written in Matlab and uses the [CVX](http://cvxr.com/cvx/) package to
solve the discussed convex problem.
The example used in the presentation can be run just using the file `main.m`.
One should note some weird results when running the code; the results always prints
something about the primal and dual problems, even when I tried to solve just one of
them (feel free to fork and make it right).
I made more detailed notes about the subject and I would be happy to share them.
If you think they could help, just drop me an email.