This paper presents a technique for building complex and adaptive meshes for urban and architecturaldesign. The combination of a self-organizing map and cellular automata algorithms stands as a method forgenerating meshes otherwise static. This intends to be an auxiliary tool for the architect or the urban planner,improving control over large amounts of spatial information. The trad...

In exploratory analysis of high-dimensional data the self-organizing map can be used to illustrate relations between the data items. We have developed two measures for comparing how diierent maps represent these relations. The other combines an index of discontinuities in the mapping from the input data set to the map grid with an index of the accuracy with which the map represents the data set...

A recurrent oscillatory self-organizing map (ROSOM) introduced. This is an architecture that assumes oscillatory states, assigned to all units, indicating their "readiness-tofire" or "exhaustion", and constitutes an internal timing mechanism. The architecture feeds the vector of all these states back into the input layer, making the units recognize and adapt to not only input but also to the en...

over the last decade or so, artificial neural networks (anns) have become one of the most promising tools formodelling hydrological processes such as rainfall runoff processes. however, the employment of a single model doesnot seem to be an appropriate approach for modelling such a complex, nonlinear, and discontinuous process thatvaries in space and time. for this reason, this study aims at de...