meteorits is a package containing several original and
flexible mixtures-of-experts models to model, cluster and classify
heteregenous data in many complex situations where the data are distributed
according to non-normal and possibly skewed distributions, and when they
might be corrupted by atypical observations. The toolbox also contains
sparse mixture-of-experts models for high-dimensional data.
meteorits contains the following Mixture-of-Experts models:
NMoE (Normal Mixtures-of-Experts) provides a flexible framework for heterogenous data with Normal expert regressors network;
SNMoE (Skew-Normal Mixtures-of-Experts) provides a flexible modeling framework for heterogenous data with possibly skewed distributions to generalize the standard Normal mixture of expert model;
tMoE (t Mixtures-of-Experts) provides a flexible and robust modeling framework for heterogenous data with possibly heavy-tailed distributions and corrupted by atypical observations;
StMoE (Skew t Mixtures-of-Experts) provides a flexible and robust modeling framework for heterogenous data with possibly skewed, heavy-tailed distributions and corrupted by atypical observations.
For the advantages/differences of each of them, the user is referred to our mentioned paper references.
To learn more about meteorits, start with the vignettes:
browseVignettes(package = "meteorits")
Chamroukhi, F. 2017. Skew-T Mixture of Experts. Neurocomputing - Elsevier 266: 390--408. https://chamroukhi.com/papers/STMoE.pdf.
Chamroukhi, F. 2016a. Robust Mixture of Experts Modeling Using the T-Distribution. Neural Networks - Elsevier 79: 20--36. https://chamroukhi.com/papers/TMoE.pdf.
Chamroukhi, F. 2016b. Skew-Normal Mixture of Experts. In The International Joint Conference on Neural Networks (IJCNN). Vancouver, Canada. https://chamroukhi.com/papers/Chamroukhi-SNMoE-IJCNN2016.pdf.
Chamroukhi, F. 2015a. Non-Normal Mixtures of Experts. http://arxiv.org/pdf/1506.06707.pdf.
Chamroukhi, F. 2015b. Statistical Learning of Latent Data Models for Complex Data Analysis. Habilitation Thesis (HDR), Universite de Toulon. https://chamroukhi.com/FChamroukhi-HDR.pdf.
Chamroukhi, F. 2010. Hidden Process Regression for Curve Modeling, Classification and Tracking. Ph.D. Thesis, Universite de Technologie de Compiegne. https://chamroukhi.com/FChamroukhi-PhD.pdf.
Chamroukhi, F., A. Same, G. Govaert, and P. Aknin. 2009. Time Series Modeling by a Regression Approach Based on a Latent Process. Neural Networks 22 (5-6): 593--602. https://chamroukhi.com/papers/Chamroukhi_Neural_Networks_2009.pdf.
Useful links: