Kernel Methods

  • Solve non-linear problems.
  • Similarity measures between two data points.
  • Moves point to different spaces in different dimensions.
  • eg. Support Vector Machine, K-means Clustering.
  • Work in feature space, not in data space.
  • Encode data into feature space.
  • Convert non-linearity to linear model.

Good Resources:


Leave a Reply

Your email address will not be published. Required fields are marked *