SVM Decision Boundary Visualizer

Visualize how Support Vector Machines classify data with different kernels

Select Class to Add Points

Click on the canvas to add data points

SVM Configuration

Kernel Type:

C (Regularization): 1.0

Gamma (γ): 0.5

Controls

Show Margins

Highlight Support Vectors

Statistics

Total Points

Class 0 Points

Class 1 Points

Support Vectors

Training Accuracy

Margin Width

About Support Vector Machines

SVMs find the optimal hyperplane that separates different classes with maximum margin. The decision boundary is determined by support vectors - the data points closest to the boundary. Different kernel functions allow SVMs to create non-linear boundaries by projecting data into higher dimensions.

Tips: Start with linearly separable data and a linear kernel. Then try the XOR pattern with an RBF kernel to see how non-linear kernels handle complex patterns. Adjust C to control the trade-off between margin width and misclassifications.