A colour quantization technique is presented which maps 24-bit colour images to 8bit colour, using Self-Organizing Neural Networks. The quantized image is superior to that produced by existing methods, and has useful continuity properties.

Time series of Circulation Weather Type (CWT), including daily averaged wind direction and vorticity, are self-classified by similarity using Kohonen Neural Networks (KNN). It is shown that KNN is able to map by similarity all 7300 five-day CWT sequences during the period of 1975-94, in London, United Kingdom. It gives, as a first result, the most probable wind sequences preceding each one of t...

In this work we are describing hardware implementation of Kohonen SelfOrganizing Map. We examined existing neurocomputers and decided to work out our own neurocomputer with a different, more suitable architecture. Our neurocomputer is being realized on FPGA (Field-Programmable Gate Array). In this article we are describing basic neurocomputer unit structure as well as linkage of these elements ...

Social Network Analysis is an approach to analysing organisations focusing on relationships as the most important aspect. In this paper we discuss visualisation techniques for Social Network Analysis, including spring-embedding and simulated annealing techniques. We introduce a visualisation technique based on Kohonen neural networks, and also introduce social flow diagrams for demonstrating th...

We designed and built a high-capacity neural network based on volume holographic interconnections in a photorefractive crystal. We used this system to implement a Kohonen topological map. We describe and justify our optical setup and present some experimental results of self-organization in the learning database.

Ce papier présente un modèle génératif et son estimation permettant la visualisation de données binaires. Notre approche est basée sur un modèle de mélange de lois de Bernoulli par blocs et les cartes de Kohonen probabilistes. La méthode obtenue se montre à la fois parcimonieuse et pertinente en pratique.

This study examines a method of analyzing the dynamics of financial failure. Using a large amount of data and a Kohonen map, we show how to depict company trajectories of behavior and movement to terminal failure. We also show how to analyze these trajectories to describe and understand the dynamics of bankruptcy and how to use them as a diagnostic tool.

An algorithm of evolving self-organizing map (ESOM) is proposed as a dynamic version of the Kohonen self-organizing map, where network structure is evolved in an on-line adaptive mode. Experiments have been carried out on some benchmark data sets as well as on macroeconomic data. Results show that ESOM is a good tool for clustering, data analysis, and visualisation.

A multi-model neural network computer has been designed and realized. A compute intensive application using the Kohonen self-organizing map, in the eld of power system monitoring , has been ported onto the neu-ral machine. The system is described and its performance is evaluated and discussed.