1. Abstract Abstract— This paper defines a new learning architecture, Layered Self-Organizing Maps (LSOMs), that uses the SOM and supervised-SOM learning algorithms. The architecture is validated with the MNIST database of hand-written digit images. LSOMs are similar to convolutional neural nets (covnets) in the way they sample data, but different in the way they represent features and learn. L...

We examine a general framework for visualizing datasets of high (> 2) dimensionality, and demonstrate it using the morphology of galaxies at moderate redshifts. The distributions of various populations of such galaxies are examined in a space spanned by four purely morphological parameters. Galaxy images are taken from the Hubble Space Telescope (HST) Wide Field Planetary Camera 2 (WFPC2) in th...

Visualization of Wikipedia categories using Self Organizing Maps shows an overview of categories and their relations, helping to narrow down search domains. Selecting particular neurons this approach enables retrieval of conceptually similar categories. Evaluation of neural activations indicates that they form coherent patterns that may be useful for building user interfaces for navigation over...

Each two years, the “Workshop on Self-Organizing Maps” (WSOM) covers the new developments in the field. The WSOM series of conferences was initiated in 1997 by Prof. Teuvo Kohonen, and has been successfully organized in 1997 and 1999 by the Helsinki University of Technology, in 2001 by the University of Lincolnshire and Humberside, and in 2003 by the Kyushu Institute of Technology. The Universi...

We present a self-organizing map model to study qualitative data (also called categorical data). It is based on a probabilistic framework which does not assume any prespecified distribution of the input data. Stochastic approximation theory is used to develop a learning rule that builds an approximation of a discrete distribution on each unit. This way, the internal structure of the input datas...

Neural networks try, in a computing way, to simulate human brain, including its behavior, by making errors and learning and thereby making new discovers. Self-organizing maps are part of a neural network group based on competitive networks where competition is used as a way of learning. They try to find similarities between data, based only on input data, grouping similar data to each other and...

In this article, the use of the self-organizing map (SOM) is approached on the basis of current theories of learning. Possibilities of computer and networked platforms that aim at helping human learning are also inspected. It is shown how the SOM can be considered a model of constructive learning. The area of constructive learning is outlined and two cases of using the self-organizing map in co...

Recent developments of Self-Organizing Maps or Kohonen networks become more and more interesting in many fields such as: pattern recognition, clustering, speech recognition, data compression, medical diagnosis... Kohonen networks is unsupervised learning models. The results obtained by the Kohonen networks are dependent on their parameters such as the architecture of the Kohonen map, the later ...

This paper presents a simple way to compensate the magnification effect of Self-Organizing Maps (SOM) when creating cartograms using CartoSOM. It starts with a brief explanation of what a cartogram is, how it can be used, and what sort of metrics can be used to assess its quality. The methodology for creating a cartogram with a SOM is then presented together with an explanation of how the magni...