Abstract
A novel on-line criterion for identifying “useless” neurons of a self-organizing network is proposed and analyzed. The criterion is based on a utility measure. When it is used in the context of the growing neural gas model to guide deletions of units, the resulting method is able to closely track non-stationary distributions. Slow changes of the distribution are handled by adaptation of existing units. Rapid changes are handled by removal of “useless” neurons and subsequent insertions of new units in other places. Additionally, the utility measure can be used to prune existing networks to a specified size with near-minimal increase of quantization error.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
H.-U. Bauer and Th. Villmann. Growing a hypercubical output space in a self-organizing feature map. TR-95-030, International Computer Science Institute, Berkeley, 1995.
B. Fritzke. Growing cell structures-a self-organizing network for unsupervised and supervised learning. Neural Networks, 7(9):1441–1460, 1994.
B. Fritzke. A growing neural gas network learns topologies. In G. Tesauro, D. S. Touretzky, and T. K. Leen, editors, Advances in Neural Information Processing Systems 7, pages 625–632. MIT Press, Cambridge MA, 1995.
B. Fritzke. Growing grid-a self-organizing network with constant neighborhood range and adaptation strength. Neural Processing Letters, 2(5):9–13, 1995.
B. Fritzke. The LBG-U method for vector quantization-an improvement over LBG inspired from neural networks. Neural Processing Letters, 5(1):35–45, 1997.
T. Kohonen. Self-organized formation of topologically correct feature maps. Biological Cybernetics, 43:59–69, 1982.
T. M. Martinetz. Competitive Hebbian learning rule forms perfectly topology preserving maps. In ICANN’93: International Conference on Artificial Neural Networks, pages 427–434, Amsterdam, 1993. Springer.
T. M. Martinetz, S. G. Berkovich, and K. J. Schulten. Neural-gas network for vector quantization and its application to time-series prediction. IEEE Transactions on Neural Networks, 4(4):558–569, 1993.
RMS91. H. J. Ritter, T. M. Martinetz, and K. J. Schulten. Neuronale Netze. Addison-Wesley, München, 1991. 2. Auflage.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fritzke, B. (1999). Be Busy and Unique — or Be History—The Utility Criterion for Removing Units in Self-Organizing Networks. In: Burgard, W., Cremers, A.B., Cristaller, T. (eds) KI-99: Advances in Artificial Intelligence. KI 1999. Lecture Notes in Computer Science(), vol 1701. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48238-5_17
Download citation
DOI: https://doi.org/10.1007/3-540-48238-5_17
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66495-6
Online ISBN: 978-3-540-48238-3
eBook Packages: Springer Book Archive