Abstract
We present a training method which adjusts the weights of the MLP (Multilayer Perceptron) to preserve the distance invariance in a low dimensional space. We apply visualization techniques to display the detailed representations of the trained neurons.
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.
References
Garrido, L., Góez, S., Roca, J.: Improved multidimensional scaling analysis using neural networks with distance-error backpropagation. Neural Networks 11(3), 595–600 (1999)
Tenenbaum, J., Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Biological Cybernetics 43(1), 59–69 (1982)
Liou, C., Tai, W.: Maximum a posteriori restoration of blurred image using self-organization. Journal of Electronic Imaging, Special Issue on Computational Intelligence in Image Processing 7, 86–93 (1998)
Liou, C.Y., Kuo, Y.T.: Economic state indicator on neuronic map. In: The 9th International Conference on Neural Information Processing (ICONIP), Singapore, pp. 787–791 (2002)
Liou, C., Tai, W.: Conformal self-organization for continuity on a feature map. neural networks. Journal of Electronic Imaging, Special Issue on Computational Intelligence in Image Processing 12, 893–905 (1999)
Liou, C.Y., Kuo, Y.T., Huang, J.C.: Smooth seamless surface construction based on conformal self-organizing map. In: King, I., Wang, J., Chan, L.-W., Wang, D. (eds.) ICONIP 2006. LNCS, vol. 4232, pp. 1012–1021. Springer, Heidelberg (2006)
Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation. In: Rumelhart, D., McClelland, J. (eds.) Parallel Distributed Processing: Explorations in the Microstructure of Cognition, pp. 318–362. MIT Press, Cambridge (1986)
Liou, C.Y., Chen, H.T., Huang, J.C.: Separation of internal representations of the hidden layer. In: Proceedings of the International Computer Symposium, ICS, Workshop on Artificial Intelligence, Chiayi, Taiwan, pp. 26–34 (2000)
Liou, C.Y., Cheng, W.C.: Resolving hidden representations. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds.) ICONIP 2007, Part II. LNCS, vol. 4985, pp. 254–263. Springer, Heidelberg (2008)
Liou, C.Y., Cheng, W.C.: Manifold construction by local neighborhood preservation. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds.) ICONIP 2007, Part II. LNCS, vol. 4985, pp. 683–692. Springer, Heidelberg (2008)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cheng, WC., Liou, CY. (2008). Manifold Construction Using the Multilayer Perceptron. In: Kůrková, V., Neruda, R., Koutník, J. (eds) Artificial Neural Networks - ICANN 2008. ICANN 2008. Lecture Notes in Computer Science, vol 5163. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-87536-9_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-87535-2
Online ISBN: 978-3-540-87536-9
eBook Packages: Computer ScienceComputer Science (R0)