Support Vector Machine
Machine Learning · Advanced
Definition
An SVM finds the boundary that separates classes with the maximum margin.
Effective in high-dimensional spaces; kernels handle non-linear data.
Diagram
Flowchart
Example: Decision rule
w, b = [1, -1], 0
for x in [(3, 1), (1, 3)]:
s = w[0]*x[0] + w[1]*x[1] + b
print(x, 'A' if s > 0 else 'B')Output: (3, 1) A (1, 3) B
Complexity
Training roughly O(n²)–O(n³)
Key points
- C controls margin vs errors
- RBF kernel is a common default
Interview questions
What are support vectors?
Training points closest to the boundary that define the margin.