computeKernel: computeKernel

In semisupKernelPCA: Kernel PCA projection, and semi-supervised variant.

Description

Compute a kernel matrix from a data set.

Usage

computeKernel(data, type=c("gaussian", "pgaussian"))

Arguments

data	n x d matrix of d-dimensional row-elements.
type	if "pgaussian", use the p-gaussian kernel function (see Francois et al. 2005). If "gaussian", use the classic gaussian kernel, ie p-gaussian function with p=2 and sigma set to the maximal pairwise distance between elements of the data set.

Value

n x n kernel matrix.

Author(s)

Pierrick Bruneau

References

Andrew Y. Ng, Michael I. Jordan, Yair Weiss
On Spectral Clustering: Analysis and an Algorithm
Neural Information Processing Symposium 2001
http://www.nips.cc/NIPS2001/papers/psgz/AA35.ps.gz Francois, D., Wertz, V. and Verleysen, M.
About the locality of kernels in high-dimensional spaces International Symposium on Applied Stochastic Models and Data Analysis 2005, pp 238-245.

See Also

computeProjectionFromKernel

Examples

data(iris)
irisdat <- as.matrix(iris[,1:4])
kernel <- computeKernel(irisdat, "pgaussian")

semisupKernelPCA documentation built on May 29, 2017, 8:59 p.m.