SVMs in Practice

Using An SVM

• Using SVM software package to solve for parameters θ

• Need to specify:

  • Choice of parameter C.
  • Choice of kenel (similarity function):
    • No kernel (“linear kernel”)

      Predict "y = 1" if θ ^T * x ≥ 0   
           
      θ0 + θ1x1 + ... θnxn ≥ 0,
      ---> n large, m small
    

    • Gaussian kernel:

DO perform feature scaling before using the Gaussian kernel

Other choices of kernel

Multi-class clasification

Logistic regression VS. SVMs

n = number of features
m = number of training examples

• if n is large (relative to m):
  • Use logistic regeression, or SVM without a kernel (“linear kernel”)
• if n is small, m is intermediate:
  • Use SVM with Gaussian kernel**
• if n is small, m is large:
  • Create / add more feature, then use logistic regression or SVM without a kernel
• Neural nerwork likely to work well for most of these settings, but may be slower to train.