Abstract
Rough neural networks aim at hierarchical construction of compound concepts. Although the structure of such concepts is assumed to be more complicated than numbers in case of standard feedforward neural networks, some mechanisms can be generalized to achieve efficient propagation and learning. One of possible generalizations, called the normalizing neural networks, enables to propagate vectors instead of single signals. Neurons take form of multidimensional functions, which model cross-dependencies among importance of particular vector components. In this way, we are able to represent some types of compound concepts using relatively simple neural network structure. As an illustration, we consider the case study related to the task of magnetic resonance images’ segmentation. We put a special emphasis on how the nature of objects and attributes in a given decision system influences the network’s architecture. We also compare our model to other rough-neural approaches.
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
Bazan, J.G., et al.: Searching for the complex decision reducts: The case study of the survival analysis. In: Zhong, N., et al. (eds.) ISMIS 2003. LNCS (LNAI), vol. 2871, pp. 160–168. Springer, Heidelberg (2003)
Chandana, S., Mayorga, R.V.: Rough Approximation based Neuro-Fuzzy Inference System. In: Proc. of IEEE HIS’2005, Rio, pp. 518–521 (2005)
Dietterich, T.: Machine learning research: four current directions. AI Magazine 18(4), 97–136 (1997)
Gibbs, J.W.: Elementary Princinples in Statistical Mechanisms. Dover, Mineola (1960)
Kaus, M., et al.: Automated Segmentation of MRI of Brain Tumors. Radiology 218, 586–591 (2001)
le Cun, Y.: A theoretical framework for backpropagation. In: Neural Networks – concepts and theory, IEEE Computer Society Press, Los Alamitos (1992)
Lingras, P.: Rough Neural Networks. In: Proc. of IPMU’1996, Granada, pp. 1445–1450 (1996)
Nguyen, H.S.: Approximate Boolean Reasoning: Foundations and Applications in Data Mining. In: Peters, J.F., Skowron, A. (eds.) Transactions on Rough Sets V. LNCS, vol. 4100, pp. 334–506. Springer, Heidelberg (2006)
Pal, S.K., Polkowski, L., Skowron, A. (eds.): Rough-Neural Computing. Cognitive Technologies Series. Springer, Heidelberg (2004)
Pawlak, Z.: Rough Sets: Theoretical Aspects of Reasoning about Data. Kluwer Academic Publishers, Dordrecht (1992)
Ślȩzak, D.: Various approaches to reasoning with frequency-based decision reducts: a survey. In: Polkowski, L., Tsumoto, S., Lin, T.Y. (eds.) Rough Set Methods and Applications: New Developments in Knowledge Discovery in Information Systems, pp. 235–285. Physica Verlag, Heidelberg (2000)
Ślȩzak, D., Szczuka, M., Wróblewski, J.: Feedforward Concept Networks. In: Dunin-Kȩplicz, B., et al. (eds.) Monitoring, Security, and Rescue Techniques in Multiagent Systems. Advances in Soft Computing, pp. 281–292. Springer, Heidelberg (2005)
Ślȩzak, D., Wróblewski, J., Szczuka, M.: Neural Network Architecture for Synthesis of the Probabilistic Rule Based Classifiers. ENTCS 82(4) (2003)
Szczuka, M.: Rough Sets and Artificial Neural Networks. In: Polkowski, L., Skowron, A. (eds.) Rough Sets in Knowledge Discovery I & II, Physica Verlag, Heidelberg (1998)
Widz, S., Revett, K., Ślȩzak, D.: A Rough Set-Based Magnetic Resonance Imaging Partial Volume Detection System. In: Pal, S.K., Bandyopadhyay, S., Biswas, S. (eds.) PReMI 2005. LNCS, vol. 3776, pp. 756–761. Springer, Heidelberg (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ślȩzak, D., Szczuka, M. (2007). Rough Neural Networks for Complex Concepts. In: An, A., Stefanowski, J., Ramanna, S., Butz, C.J., Pedrycz, W., Wang, G. (eds) Rough Sets, Fuzzy Sets, Data Mining and Granular Computing. RSFDGrC 2007. Lecture Notes in Computer Science(), vol 4482. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72530-5_69
Download citation
DOI: https://doi.org/10.1007/978-3-540-72530-5_69
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72529-9
Online ISBN: 978-3-540-72530-5
eBook Packages: Computer ScienceComputer Science (R0)