… The degree of freedom of the t distribution is self-adaptive to the quality of the data set. A
large degree of freedom indicates a good quality of the data set while a small one corresponds …

… mixture model for which we have a normal EM algorithm. Compared to other mixture model
approaches to self-… and a penalty term that enforces self-organization. Our approach allows …

… We consider such mixture models for both univariate as well as multivariate data. This
allows robust modeling of high-dimensional multimodal and asymmetric data generated by …

… (ICA) and self-organizing maps (SOM) [31], and t-… t-mixture model with missing information
(by simply exploiting the same strategy as in Subsection 2.2) to obtain a modified t-mixture …

… we delineate a broad class of self-reciprocal distributions. … As a possible model behind a
normal variance-mean mixture … , t = 3 = 0 and A = I then (2.5) is the r-dimensional t distribution. …

… In this paper, we use this formulation of the skew- t distribution to introduce a skew- t
analogue of the mixture of factor analyzers model, as well as a family of parsimonious models …

… fundamental dataset models such as Gaussian mixtures and conducting … self-training under
a Gaussian mixture model (GMM). We precisely calculate the distributional properties of self-…

… It reveals the need for an analysis using multivariate mixture distribution models, … models
for every scale of the PSDQ within each latent group. If the results show that a Rasch model can …

… and unrestricted skew mixture models in clustering, … mixtures of skew normal and \(t\)-component
distributions with other non-normal component distributions, including mixtures …

… that mixture models can be learned to within ε of the Bayes-optimal accuracy using at most
O(d) labeled examples and O(d/ε2) unlabeled examples by way of a semi-supervised self-…