Generative Histogram-Based Model Using Unsupervised Learning
Résumé
This paper presents a new generative unsupervised learning algorithm based on a representation of the clusters distribution by histograms. The main idea is to reduce the model complexity through cluster-defined projections of the data on independent axes. The results show that the proposed approach performs efficiently compared with other algorithms. In addition, it is more efficient to generate new instances with the same distribution than the training data.