Abstract
The learning of complex relationships can be decomposed into several neural networks. The modular organization is determined by prior knowledge of the problem that permits to split the processing into tasks of small dimensionality. The sub-tasks can be implemented with neural networks, although the learning examples cannot be used anymore to supervise directly each of the networks. This article addresses the problem of learning in a modular context, developing in particular additive compositions. A simple rule allows defining efficient training, and combining, for example, several Supervised-SOM networks. This technique is important because it introduces interesting generalizations in many modular compositions, permitting data fusion or sequential combinations of neural networks.
Similar content being viewed by others
References
Caelli, T., Guan, L. and Wen, W.: Modularity in Neural Computing, Proceedings of the IEEE 87(9) (1999), 1497–1518.
Hastie, T. J. and Tibshirani, R. J.: Generalized Additive Models, Chapman and Hall, London, 1990.
Kohonen, T.: Self-Organizing Maps, Springer-Verlag, Berlin, 1995.
Ritter, H. J., Martinetz, T. M. and Schulten, K. J.: Neural Computation and Self-Organizing Maps, Addison-Wesley, Reading, MA, 1992.
Principe, J. C., Wang, L. and Motter, M. A.: Local Dynamic Modeling with Self-Organizing Maps and Applications to Nonlinear System Identification and Control, Proceedings of the IEEE 86(11) (1998), 2240–2258.
Widrow, B. and Walach, E.: Adaptive Inverse Control, PrenticeHall Press, Upper Saddle River, NJ, 1996.
Haykin, S.: Neural Networks: A Comprehensive Foundation, Macmillan College Publishing Company, Inc., New York, 1994.
Buessler, J.-L.: Modular Neural Network Architectures Applied to the Visual Servoing of Robotic Systems, PhD Thesis (in French), Univ. of Mulhouse, France, 1999.
Buessler, J.-L. and Urban, J.-P.: Visually guided movements: learning with modular neural maps in robotics, Neural Networks 11(7–8) (1998), 1395–1415.
Miller, W. T., III, Glanz, F. H. and Kraft, L. G.: CMAC: An Associative Neural Network Alternative to Backpropagation, Proceedings of the IEEE 78(10) (1990), 1561–1567.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Buessler, JL., Urban, JP. & Gresser, J. Additive Composition of Supervised Self-Organizing Maps. Neural Processing Letters 15, 9–20 (2002). https://doi.org/10.1023/A:1013892727067
Issue Date:
DOI: https://doi.org/10.1023/A:1013892727067