We present an expectation-maximization (EM) algorithm that yields topology preserving maps of data based on probabilistic mixture models. Our approach is applicable to any mixture model for which we have a normal EM algorithm. Compared to other mixture model approaches to self-organizing maps, the function our algorithm maximizes has a clear interpretation: it sums data log-likelihood and a pen...

We present a framework in which self-organizing systems can be used to perform change of representation on knowledge discovery problems, to learn from very large databases. Clustering using self-organizing maps is applied to produce multiple, intermediate training targets that are used to define a new supervised learning and mixture estimation problem. The input data is partitioned using a stat...

In this paper we introduce a MapReduce-based implementation of self-organizing maps that performs compute-bound operations on distributed GPUs. The kernels are optimized to ensure coalesced memory access and effective use of shared memory. We have performed extensive tests of our algorithms on a cluster of eight nodes with two NVidia Tesla M2050 attached to each, and we achieve a 10x speedup fo...

This paper deals with the Kohonen Self-organizing maps for cluster analysis applications. The cluster analysis represents a group of methods whose aim is to classify the objects into clusters. For solving cluster analysis applications many new algorithms using neural networks have been used. This paper describes the use of an advanced method of neural network represented by Kohonen self-organiz...

Self-Organizing Maps, or Kohonen networks, are a widely used neural network architecture. This paper starts with a brief overview of how selforganizing maps can be used in different types of problems. A simple and intuitive explanation of how a self-organizing map is trained is provided, together with a formal explanation of the algorithm, and some of the more important parameters are discussed...