Growing Self-Organizing Maps for Data Analysis

Growing Self-Organizing Maps for Data Analysis

Soledad Delgado (Technical University of Madrid, Spain), Consuelo Gonzalo (Technical University of Madrid, Spain), Estíbaliz Martínez (Technical University of Madrid, Spain) and Águeda Arquero (Technical University of Madrid, Spain)
Copyright: © 2009 |Pages: 7
DOI: 10.4018/978-1-59904-849-9.ch116
OnDemand PDF Download:
No Current Special Offers


Currently, there exist many research areas that produce large multivariable datasets that are difficult to visualize in order to extract useful information. Kohonen selforganizing maps have been used successfully in the visualization and analysis of multidimensional data. In this work, a projection technique that compresses multidimensional datasets into two dimensional space using growing self-organizing maps is described. With this embedding scheme, traditional Kohonen visualization methods have been implemented using growing cell structures networks. New graphical map displays have been compared with Kohonen graphs using two groups of simulated data and one group of real multidimensional data selected from a satellite scene.
Chapter Preview

Growing Cell Structures Visualization

This work studies the GCS networks to obtain an embedding method to project the bi-dimensional output map, with the aim of generating several graphic map displays for the exploratory data analysis during and after the self-organization process.

Key Terms in this Chapter

Artificial Neural Networks: An interconnected group of units or neurons that uses a mathematical model for information processing based on a connectionist approach to computation.

Growing Cell Structures: Growing variant of the self-organizing map model, with the peculiarity of dynamically adapts the size and connections of the output layer to the characteristics of the training patterns.

Unsupervised Learning: Method of machine learning where a model is fit to observations. It is distinguished from supervised learning by the fact that there is no a priori output.

Data Mining: The application of analytical methods and tools to data for the purpose of identifying patterns, relationships or obtaining systems that perform useful tasks such as classification, prediction, estimation, or affinity grouping.

Self-Organizing Map: A subtype of artificial neural network. It is trained using unsupervised learning to produce low dimensional representation of the training samples while preserving the topological properties of the input space

Exploratory Data Analysis: Philosophy about how a data analysis should be carried out. Exploratory data analysis employs a variety of techniques (mostly graphical) to extract the knowledge inherent to the data.

Knowledge Visualization: The creation and communication of knowledge through the use of computer and non-computer-based, complementary, graphic representation techniques.

Complete Chapter List

Search this Book: