Abstract
In this work we present a modified Nonnegative Matrix Factorization (NMF) method for learning a mixture of local SOM models. The proposed method approximates a data point with a linear combination of its k-nearest neighbor prototypes. This allows obtaining a low quantization error and at the same time keeping the interpretability of the prototypes. The results of the new method are compared with those obtained using non-negative least squares, NMF and SOM, using four benchmark data sets. Two metrics are used to assess the performance of the different approaches. The proposed k-nn NMF method obtained the lowest relative local quantization error, while keeping a global quantization error similar to the best alternative methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Côme, E., Cottrell, M., Gaubert, P.: Professional trajectories of workers using disconnected self-organizing maps. In: Estevez, P.A., Principe, J.C., Zegers, P. (eds.) Advances in Self-Organizing Maps. AISC, vol. 198, pp. 295–304. Springer, Heidelberg (2013)
Fritzke, B., et al.: A growing neural gas network learns topologies. Advances in Neural Information Processing Systems 7, 625–632 (1995)
Hartigan, J.A., Wong, M.A.: Algorithm as 136: A k-means clustering algorithm. Journal of the Royal Statistical Society. Series C 28(1), 100–108 (1979)
Kim, H., Park, H.: Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis. Bioinformatics 23(12), 1495–1502 (2007)
Kim, H., Park, H.: Nonnegative matrix factorization based on alternating nonnegativity constrained least squares and active set method. SIAM Journal on Matrix Analysis and Applications 30(2), 713–730 (2008)
Kim, J., Park, H.: Sparse nonnegative matrix factorization for clustering. Technical Report Technical report GT-CSE-08-01, Georgia Institute of Technology (2008)
Kohonen, T.: Self-organizing maps. Springer-Verlag New York, Inc., Secaucus (1997)
Kohonen, T.: Description of input patterns by linear mixtures of som models. In: Proceedings of WSOM, Bielefeld, Germany (2007)
Kohonen, T.: Essentials of the self-organizing map. Neural Networks 37, 52–63 (2013)
Kohonen, T., Nieminen, I.T., Honkela, T.: On the quantization error in SOM vs. VQ: A critical and systematic study. In: PrÃncipe, J.C., Miikkulainen, R. (eds.) WSOM 2009. LNCS, vol. 5629, pp. 133–144. Springer, Heidelberg (2009)
Labusch, K., Barth, E., Martinetz, T.: Sparse coding neural gas for the separation of noisy overcomplete sources. In: Kůrková, V., Neruda, R., KoutnÃk, J. (eds.) ICANN 2008, Part I. LNCS, vol. 5163, pp. 788–797. Springer, Heidelberg (2008)
Labusch, K., Barth, E., Martinetz, T.: Sparse coding neural gas: Learning of overcomplete data representations. Neurocomputing 72(7), 1547–1555 (2009)
Lin, C.J.: On the convergence of multiplicative update algorithms for nonnegative matrix factorization. IEEE Trans. on Neural Networks 18(6), 1589–1596 (2007)
Martinetz, T.M., Berkovich, S.G., Schulten, K.J.: Neural-gas’ network for vector quantization and its application to time-series prediction. IEEE Trans. on Neural Networks 4(4), 558–569 (1993)
Nova, D., Estévez, P.A.: A review of learning vector quantization classifiers. Neural Computing and Applications (2014), doi:10.1007/s00521-013-1535-3
Oja, E.: Simplified neuron model as a principal component analyzer. Journal of Mathematical Biology 15(3), 267–273 (1982)
Principe, J.C., Wang, L.: Non-linear time series modeling with self-organization feature maps. In: Proceedings of the 1995 IEEE Workshop on Neural Networks for Signal Processing V, pp. 11–20. IEEE (1995)
Principe, J.C., Wang, L., Motter, M.A.: Local dynamic modeling with self-organizing maps and applications to nonlinear system identification and control. Proceedings of the IEEE 86(11), 2240–2258 (1998)
Seung, D., Lee, L.: Algorithms for non-negative matrix factorization. Advances in Neural Information Processing Systems 13, 556–562 (2001)
Ultsch, A.: Clustering with som: U*c. In: Proceedings of WSOM, pp. 75–82 (2005)
Wold, S., Esbensen, K., Geladi, P.: Principal component analysis. Chemometrics and Intelligent Laboratory Systems 2(1), 37–52 (1987)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Nova, D., Estévez, P.A., Huijse, P. (2014). K-Nearest Neighbor Nonnegative Matrix Factorization for Learning a Mixture of Local SOM Models. In: Villmann, T., Schleif, FM., Kaden, M., Lange, M. (eds) Advances in Self-Organizing Maps and Learning Vector Quantization. Advances in Intelligent Systems and Computing, vol 295. Springer, Cham. https://doi.org/10.1007/978-3-319-07695-9_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-07695-9_22
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07694-2
Online ISBN: 978-3-319-07695-9
eBook Packages: EngineeringEngineering (R0)