# Support Vector Machine

Note: this post meant to help clarify the tutorial question number 2  for COMP 9417 – Week 9, School of Computer Science and Engineering, UNSW (s1 – 2017)

Support Vector Machine

Support Vector Machine (SVM) is essentially an approach to learning linear classifiers  which enables SVM to maximising the margin. Here is the picture, inspired by Flach – Fig. 7.6 – 7.7, that shows the difference between decision boundary produced by SVM, and other linear classifiers (such as: linear regression or perceptron).

To achieve that, SVM utilise below objective function, which attempts to find the values of $alpha_1,...,alpha_n$ that maximise the function.

To solve that equation, quadratic optimization solvers typically is used. However, for a simple toy example, we can compute it manually. Here are steps to find a solution for the weight vector $textbf{w}$, threshold $t$, and the margin $m$ (from slides 23-28):

1. Set up Gram matrix for labelled data
2. Set up expression to be minimised
3. Take partial derivatives
4. Set to zero and solve for each multiplier
5. Solve $textbf{w}$
6. Solve $t$
7. Solve $m$

Here are the detail solutions:

Sources:

• Lecture slide Supervised Learning – Kernel Methods, Mike Bain, CSE – UNSW
• Tutorial questions and solutions of Kernel Methods, Mike Bain, CSE – UNSW
• Flach, P. (2012). Machine learning: the art and science of algorithms that make sense of data. Cambridge University Press
Advertisements