Visualizing Hierarchical Representation in a Multilayered Restricted RBF Network
In this study we propose a hierarchical neural network that is able to generate a topographical map in its internal layer. The map significantly differs from the conventional Kohonen’s SOM, in that it preserves the topological characteristics in relevance to the context, for example the labels, of the data. This map is useful if we are interested in visualizing the underlying characteristics of the classificability of the data that traditionally cannot be visualized with the standard SOM. In this paper, we expand our network into a multilayered structure that allows us visualize and thus better understand on how the neural network perceives the given data in the light of classification task.
KeywordsSelf-Organizing Map Supervised Learning Hierarchical Representation
Unable to display preview. Download preview PDF.
- 1.Hartono, P., Trappenberg, T.: Classificability-regulated Self-Organizing Map using Restricted RBF. In: Proc. IEEE Int. Joint Conference on Neural Networks (IJCNN 2013), pp. 160–164 (2013)Google Scholar
- 5.Yin, H.: ViSOM-A Novel Method for Multivariate Data Projection and Structure Visualization. IEEE Trans. Neural Networks 13(1), 237–243 (2002)Google Scholar
- 6.Wu, S., Chow, T.W.S.: PRSOM: A New Visualization Method by Hybridizing Multidimensional Scaling and Self-Organizing Map. IEEE Trans. on Neural Networks 16(6), 1362–1380 (2005)Google Scholar
- 10.Rumelhart, D., McClelland, J.: Learning Internal Representation by Error Propagation. Parallel Distributed Processing, vol. 1, pp. 318–362. MIT Press (1984)Google Scholar
- 12.Duin, R.P.W., et al.: PRTools4, A Matlab Toolbox for Pattern Recognition. Delft University of Technology (2007)Google Scholar