Recent Advances with the Growing Hierarchical Self-Organizing Map
We present our recent work on the Growing Hierarchical Self-Organizing Map, a dynamically growing neural network model which evolves into a hierarchical structure according to the necessities of the input data during an unsupervised training process. The benefits of this novel architecture are shown by organizing a real-world document collection according to semantic similarities.
KeywordsWeight Vector Neural Network Model Internal Affair Neighboring Unit Neighboring Branch
Unable to display preview. Download preview PDF.
- 1.M. Dittenbach, D. Merkl, and A. Rauber. The growing hierarchical self-organizing map. In Proc Int’l Joint Conf Neural Networks, Como, Italy, 2000.Google Scholar
- 2.B. Fritzke. Growing Grid - A self-organizing network with constant neighborhood range and adaption strength. Neural Processing Letters, 2(5), 1995.Google Scholar
- 3.T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43, 1982.Google Scholar
- 4.T. Kohonen. Self-organizing maps. Springer-Verlag, Berlin, 1995.Google Scholar
- 5.P. Koikkalainen. Fast deterministic self-organizing maps. In Proc Int’l Conf Neural Networks, Paris, Prance, 1995.Google Scholar
- 6.P. Koikkalainen and E. Oja. Self-organizing hierarchical feature maps. In Proc Int’l Joint Conf Neural Networks, San Diego, CA 1990.Google Scholar
- 7.D. Merkl and A. Rauber. Automatic labeling of self-organizing maps for information retrieval. In Proc Int’l Conf Neural Information Processing, Perth, Australia, 1999.Google Scholar
- 8.R. Miikkulainen. Script recognition with hierarchical feature maps. Connection Science, 2, 1990.Google Scholar
- 9.G. Salton. Automatic Text Processing: The Transformation, Analysis, and Retrieval of Information by Computer. Addison-Wesley, Reading, MA, 1989.Google Scholar