Shiksha Nation
Skip to content

Kernel principal component analysis

Multivariate statistical technique

  • 4 min read
  • 5 chapters

Related on Lably

Through Dot product and Data set

Background: Linear PCA

Recall that conventional PCA operates on zero-centered data; that is,

1N∑i=1Nxi=0,

where xi is one of the N multivariate observations. It operates by diagonalizing the covariance matrix,

C=1N∑i=1Nxixi⊤

in other words, it gives an eigendecomposition of the covariance matrix:

λv=Cv

which can be rewritten as

λxi⊤v=xi⊤Cvfori=1,…,N.

(See also: Covariance matrix as a linear operator)

Sign up free to read the rest

4 more chapters are free with a Lably account.

Already have an account?

More in Robotics