You are interested in Support Vector Machine (SVM) and want to learn more about them ?
You are in the right place. I created this site in order to share tutorials about SVM.
If you wish to have an overview of what SVMs are, you can read this article
This is a free-ebook which covers a broad range of topics.
Understanding the math series
- Part 1: What is the goal of the Support Vector Machine (SVM)?
- Part 2: How to compute the margin?
- Part 3: How to find the optimal hyperplane?
- Part 4: Unconstrained minimization
- Part 5: Convex functions
- Part 6: Duality and Lagrange multipliers
SVM are known to be difficult to grasp. Many people refer to them as "black box".
This tutorial series is intended to give you all the necessary tools to really understand the math behind SVM.
It starts softly and then get more complicated. But my goal here is to keep everybody on board, especially people who do not have a strong mathematical background.
SVM R tutorials
R is a good language if you want to experiment with SVM.
So I wrote some introductory tutorials about it.
The article about Support Vector Regression might interest you even if you don't use R.
Machine learning languages of choice are often Python, R and Matlab. But you can also play with SVM if you are a C# afficionados.
I recently found the Accord.NET machine learning framework. Which looks very powerful. So you might want to take a look at it to do machine learning in C#.
Text classification tutorials
SVM can be applied to a wide variety of subjects. One of them is text classification. In the following tutorials you will learn how to transform text into data that you can feed to your SVM.
You will then see how to use this data to perform text classification (in R or in C#)
- How to prepare your data for text classification?
- How to classify text in R ?
- How to classify text in C# ?
Another article explains why the linear kernel is often the choice giving the best results in text classification: