Abstract
Visualization of neural network learning faces the problem of overwhelming amount of visual information. This paper describes the application of clustering methods for reduction of visual information in the response function visualization. If only clusters of neurons are visualized instead of direct visualization of responses of all neurons in the network, the amount of visually presented information can be significantly reduced. This is useful for user fatigue reduction and also for minimization of the visualization equipment requirements. We show that application of Kohonen network or Growing Neural Gas with Utility Factor algorithm allows to visualize the learning of moderate-sized neural networks. Comparison of both algorithms in this task is provided, also with performance analysis and example results of response function visualization.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Užák, M., Jakša, R.: Framework for the interactive learning of artificial neural networks. In: Kollias, S.D., Stafylopatis, A., Duch, W., Oja, E. (eds.) ICANN 2006. LNCS, vol. 4131, pp. 103–112. Springer, Heidelberg (2006)
Craven, M.W., Shavlik, J.W.: Visualizing learning and computation in artificial neural networks. International Journal on Artificial Intelligence Tools (1), 399–425 (1991)
Lang, K.J., Witbrock, M.J.: Learning to tell two spirals apart. In: Proceedings of the 1988 Connectionist Models Summer School, pp. 52–59 (1988)
Jakša, R., Takagi, H.: Tuning of image parameters by interactive evolutionary computation. In: Proc. of 2003 IEEE International Conference on Systems, Man & Cybernetics (SMC 2003), pp. 492–497 (2003)
Kohonen, T.: Self-organized formation of topologically correct feature maps. Neurocomputing: foundations of research, pp. 509–521 (1982)
Fritzke, B.: A growing neural gas network learns topologies. In: Tesauro, G., Touretzky, D.S., Leen, T.K. (eds.) Advances in Neural Information Processing Systems, vol. 7, pp. 625–632. MIT Press, Cambridge (1995)
Fritzke, B.: A self-organizing network that can follow non-stationary distributions. In: Gerstner, W., Hasler, M., Germond, A., Nicoud, J.-D. (eds.) ICANN 1997. LNCS, vol. 1327, pp. 613–618. Springer, Heidelberg (1997)
Kohonen, T.: Automatic formation of topological maps of patterns in a self organizing system. In: Oja, E., Simula, O. (eds.) 2nd Scand. Conference on Image Analysis, pp. 214–220 (1981)
Pratihar, D., Hayashida, N., Takagi, H.: Comparison of mapping methods to visualize the EC landscape. In: 5th International Conference on Knowledge-Based Intelligent Information Engineering Systems & Allied Technologies (KES 2001), pp. 223–227 (2001)
Takagi, H.: Interactive evolutionary computation: Fusion of the capabilities of EC optimization and human evaluation. Proceedings of the IEEE 89(9), 1275–1296 (2001)
Holmström, J.: Growing Neural Gas - experiments with GNG, GNG with Utility and supervised GNG. Master’s thesis, Uppsala University (August 2002)
Kangas, J., Kohonen, T., Laaksonen, J.: Variants of self-organizing maps. IEEE Transactions on Neural Networks 1, 93–99 (1990)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Užák, M., Jakša, R., Sinčák, P. (2008). Reduction of Visual Information in Neural Network Learning Visualization. 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_71
Download citation
DOI: https://doi.org/10.1007/978-3-540-87536-9_71
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)