cs3002-supervised-learning-knearest-neighbour

• K-nearest neighbour is based on the idea that nearby data points influence classification.

• Case based reasoning.

• Based on the idea that items that are located “nearby” in the data space will influence how unknown data is classified.

• Been around since 1910.

• Requires:

  • Distance Metric.
    • Euclidian.
    • Correlation.
    • Mahalanobis.
  • $k$ parameter (no. of neighbours).
  • Weighting Function.
  • How to combine info from neighbours.

• Example:

  • Metric: Euclidian.
  • No weighting function.
  • Maximum vote of neighbours.

Demo can be found here