EMNearestMeanClassifier: Semi-Supervised Nearest Mean Classifier using Expectation...

In RSSL: Implementations of Semi-Supervised Learning Approaches for Classification

Semi-Supervised Nearest Mean Classifier using Expectation Maximization

Description

Expectation Maximization applied to the nearest mean classifier assuming Gaussian classes with a spherical covariance matrix.

Usage

EMNearestMeanClassifier(X, y, X_u, method = "EM", scale = FALSE,
  eps = 1e-04)

Arguments

X	matrix; Design matrix for labeled data
y	factor or integer vector; Label vector
X_u	matrix; Design matrix for unlabeled data
method	character; Currently only "EM"
scale	Should the features be normalized? (default: FALSE)
eps	Stopping criterion for the maximinimization

Details

Starting from the supervised solution, uses the Expectation Maximization algorithm (see Dempster et al. (1977)) to iteratively update the means and shared covariance of the classes (Maximization step) and updates the responsibilities for the unlabeled objects (Expectation step).

References

Dempster, A., Laird, N. & Rubin, D., 1977. Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society. Series B, 39(1), pp.1-38.

RSSL documentation built on March 31, 2023, 7:27 p.m.