PATTERNIZING COMMUNITIES BY USING AN ARTIFICIAL NEURAL-NETWORK

The Kohonen network, an unsupervised learning algorithm in artificial neural networks, performs self-organizing mapping and reduces dimensio ns of a complex data set. In this study, the network was applied to cl ustering and patternizing community data in ecology. The input data we re benthic macroinvertebrates collected at study sites in the Suyong r iver in Korea. The grouping resulting from learning by the Kohonen net work was comparable to the classification by conventional clustering m ethods. Through patternizing, the network showed a possibility of prod ucing easily comprehensible low-dimensional maps under the total confi guration of community groups in a target ecosystem. Changes in spatio- temporal community patterns may also be traced through the recognition process.