- Linear Support Vector Machine
Given a set of points
with label
The SVM finds a hyperplane defined by the pair (w,b)
(where w is the normal to the plane and b is the distance from the origin)
s.t.
- What if the data is not linearly separable?
- Project the data to high dimensional space where it is linearly separable and then we can use linear SVM – (Using Kernels)
Classification using SVM (w,b)
In non linear case we can see this as
Kernel – Can be thought of as doing dot product in some high dimensional space
Example of Non-linear SVM
SVM
- Relatively new concept
- Nice Generalization properties
- Hard to learn – learned in batch mode using quadratic programming techniques
- Using kernels can learn very complex functions
SVM Related Links