mlbench.ringnorm {mlbench}

Ringnorm Benchmark Problem

Description

The inputs of the ringnorm problem are points from two Gaussian distributions. Class 1 is multivariate normal with mean 0 and covariance 4 times the identity matrix. Class 2 has unit covariance and mean (a,a,\ldots,a), a=d^{-0.5}.

Usage

mlbench.ringnorm(n, d=20)

Arguments

n

number of patterns to create

d

dimension of the ringnorm problem

Value

Returns an object of class "mlbench.ringnorm" with components

x

input values

classes

factor vector of length n with target classes

References

Breiman, L. (1996). Bias, variance, and arcing classifiers. Tech. Rep. 460, Statistics Department, University of California, Berkeley, CA, USA.

Examples

p<-mlbench.ringnorm(1000, d=2)
plot(p)