Abstract
In this paper, we propose a novel artificial neural network, called self-adjusting feature map (SAM), and its unsupervised learning algorithm with self-adjusting mechanism. After the training of SAM network, we will obtain a map composed of a set of representative connected neurons. The trained network structure of representative connected neurons not only displays the spatial relation of the input data distribution but also quantizes the data well. SAM can automatically isolate a set of connected neurons, in which the number of the set may indicate the number of clusters to be used. The idea of self-adjusting mechanism is based on combining of mathematical statistics and neurological advance and retreat of waste. For each representative neuron, there are three periods, growth, adaptation and decline, in its training process. The network of representative neurons will first create the necessary neurons according to the local density of the input data in the growth period. Then it will adjust neighborhood neuron pair’s connected/disconnected topology constantly according to the statistics of input feature data in the adaptation period. Lastly the unnecessary neurons of the network will be merged or deleted in the decline period. In this study, we exploit SAM to handle some peculiar cases that cannot be well dealt with by classical unsupervised learning networks such as self-organizing feature map (SOM) network. Furthermore, we also take several real world cases to exhibit the remarkable characteristics of SAM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kohonen, T.: Self Organization and Associative Memory, 2nd edn. Springer Ser. Inform, vol. 8. Springer, New York (1984)
Kangas, J., Kohnen, T., Laaksonen, J.: Variants of self-organizing maps. IEEE Trans. Neural Networks 1, 93–99 (1990)
Rumelhart, D.E., McClelland, J.L.: The PDP research group: Parallel Distributed Processing, vol. 1, pp. 151–193. MIT Press, Cambridge (1986)
Mulier, F., Cherkassky, V.: Statistical analysis of self-organization. Neural Networks 8(5), 717–727 (1995)
Choi, D.-I., Park, S.-H.: Self-creating and Organizing Neural Networks. IEEE Trans. Neural Network 5(4), 561–575 (1994)
Fritzke, B.: Growing cell structures a self-organizing neural networks for unsupervised and supvised learning. Neural Networks 7(9), 1441–1460 (1994)
Fritzke, B.: A growing neural gas network learns topologies. In: Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)
Wang, J.-H., Sun, W.-D.: Online learning vector quantization: A harmonic competition approach based on conservation network. IEEE Trans. Syst. Man, Cybern.-Part B: Cybern. 29, 642–653 (1999)
Xiong, H., Ahmad, M.O., King, I.: Branching competitive learning Network: A novel self-creating model. IEEE Trans. Neural Networks 15, 417–429 (2004)
Martinetz, M., Schulten, K.J.: A “neural-gas” network learns topologies. In: Kohonen, K., Simula, O., Kangas, J. (eds.) Artif. Neural Netw., pp. 397–402. North-Holland, Amsterdam (1991)
Matsuyama, Y.: Harmonic competition: A self-organizing multiple criteria optimization. IEEE Trans. Neural Networks 7, 652–668 (1996)
Ritter, H., Martinetz, T., Schulten, K.: Neural Computation and Self-Organizing Map: An Introduction. Addison-Wesley, Reading (1992)
Brugger, D., Bogdan, M., Rosenstiel, W.: Automatic Cluster Detection in Kohonen’s SOM. IEEE Trans. Neural Networks 19(3), 442–459 (2008)
Yin, H.: ViSOM: A novel method for multivariate data projection and structure visualization. IEEE Trans. Neural Networks 13(1), 237–243 (2002)
Wu, S., Chow, T.W.S.: PRSOM: a new visualization method by hybridizing multidimensional scaling and self-organizing map. IEEE Trans. Neural Networks 16(6), 1362–1380 (2005)
Yen, G.G., Wu, Z.: Ranked Centroid Projection: A Data Visualization Approach With Self-Organizing Maps. IEEE Trans. Neural Networks 19(2) (2008)
Tasdemir, K., Merenyi, E.: Exploiting Data Topology in Visualization and Clustering of Self-Organizing Maps. IEEE Trans. Neural Networks 20(4), 549–562 (2009)
Fritzke, B.: A self-organizing network that can follow nonstationary distributions. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 613–618. Springer, Heidelberg (1997)
Datta, A., Pal, T., Parui, S.K.: A modified self-organizing neural net for shape extraction. Neurocomputing 14(1), 3–14 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lin, CT., Li, DL., Chang, JY. (2011). Self-Adjusting Feature Maps Network. In: Lu, BL., Zhang, L., Kwok, J. (eds) Neural Information Processing. ICONIP 2011. Lecture Notes in Computer Science, vol 7064. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-24965-5_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-24965-5_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-24964-8
Online ISBN: 978-3-642-24965-5
eBook Packages: Computer ScienceComputer Science (R0)