The Self-Organizing Map (SOM) is one of the most frequently used architectures for unsupervised artificial neural networks. Introduced by Teuvo Kohonen in the 1980s, SOMs have been developed as a very powerful method for visualization and unsupervised classification tasks by an active and innovative community of interna­ tional researchers. A number of extensions and modifications have been developed during the last two decades. The reason is surely not that the original algorithm was imperfect or inad­ equate. It is rather the universal applicability and easy handling of the SOM. Com­ pared to many other network paradigms, only a few parameters need to be arranged and thus also for a beginner the network leads to useful and reliable results. Never­ theless there is scope for improvements and sophisticated new developments as this book impressively demonstrates. The number of published applications utilizing the SOM appears to be unending. As the title of this book indicates, the reader will benefit from some of the latest the­ oretical developments and will become acquainted with a number of challenging real-world applications. Our aim in producing this book has been to provide an up­ to-date treatment of the field of self-organizing neural networks, which will be ac­ cessible to researchers, practitioners and graduated students from diverse disciplines in academics and industry. We are very grateful to the father of the SOMs, Professor Teuvo Kohonen for sup­ porting this book and contributing the first chapter.

Inhalt

Overture.- Measures for the Organization of Self-Organizing Maps.- Unsupervised Learning and Self-Organization in Networks of Spiking Neurons.- Generative Probability Density Model in the Self-Organizing Map.- Growing Multi-Dimensional Self-Organizing Maps for Motion Detection.- Extensions and Modifications of the Kohonen-SOM and Applications in Remote Sensing Image Analysis.- Modeling Speech Processing and Recognition in the Auditory System Using the Multilevel Hypermap Architecture.- Algorithms for the Visualization of Large and Multivariate Data Sets.- Self-Organizing Maps and Financial Forecasting: an Application.- Unsupervised and Supervised Learning in Radial-Basis-Function Networks.- Parallel Implementations of Self-Organizing Maps.