GENDATG

Generation of a 2D classification problem: Gaussian circle and blob

    A = GENDATG(N,S1,S2)

Input
N	Dataset size, or 2-element array of class sizes (default: [50 50]).
S1	Standard deviation of the circle, default 0.1
S2	Standard deviation of the blob, default 0.3.

Output
A	Dataset.

Description

Generation of a two-class problem. The first class is a set of uniformly  distributed points on the unit circle with a normally distributed  Gaussian radial deviation. The second class is a Gaussian distributed  2D spherical dataset in the origin with standard deviation S2.

See also

datasets, prdatasets,