Abstract
The article presents methods of dealing with huge data in the domain of neural networks. The decomposition of neural networks is introduced and its efficiency is proved by the authors’ experiments. The examinations of the effectiveness of argument reduction in the above filed, are presented. Authors indicate, that decomposition is capable of reducing the size and the complexity of the learned data, and thus it makes the learning process faster or, while dealing with large data, possible. According to the authors’ experiments, in some cases, argument reduction, makes the learning process harder.
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
R. L. Ashenhurst, The Decomposition of Switching Functions, Proc. Int. Symp. of Theory. of Switching, 1957.
S. Chang, M. Marek-Sadowska, T. Hwang, Technology mapping for TLU FPGA’s based on decomposition of Binary Decision Diagrams, IEEE Transaction on Computers, vol. 15, No. 10, 1996.
H. A. Curtis, A New Approach to the Design of Switching Circuits, Princeton, N.J., Van Nostrand, 1962.
S. Y. Kung, Digital Neural Networks, PTR Prentice Hall, 1993.
Y. Lai, K. Pan, M. Pedram, OBDD-based functional decomposition: algorithms and implementation, IEEE Transaction on Computers, vol. 15, No. 8, 1996.
Y. Lai, M. Pedram, S. Vrudhula, EVOBDD-based algorithms for integer linear programming, spectral transformation, and functional decomposition, IEEE Transaction on Computers, vol. 13, No. 8, 1994.
T. Luba, Decomposition of multiple-valued functions, Proc. IEEE-ISMVL, USA, 1995.
T. Luba, C. Moraga, S. Yanushkevich, M. Opoka, V. Shmerko Evolutionary Multi-Level Network Synthesis in Given Design Style, Proc. IEEE-ISMVL, Portland, Oregon, USA, 2000.
T. Luba, H. Niewiadomski, H. Pleban, H. Selvaraj, P. Sapiecha, Functional decomposition and its application in design of digital circuits and machine learning, TASTED Inter. Conf. On Applied Informatics, Innsbruck, Austria, 2001.
T. Masters, Neural Networks in Practice, Prentice-Hall, 1996.
Z. Pawlak, Rough Sets: Theoretical Aspects of Reasoning About Data, Kluwer, 1991
M. Perkowski, R. Malvi, S. Grygiel, M. Burns, A. Mishchenko, Graph coloring algorithms for fast evaluation of Curtis decomposifons, DAC, 1999.
P. Sapiecha, H. Selvaraj, M. Pleban, Decomposition of Boolean Relations and Functions in Logic Synthesis and Data Analysis, The Second International Conference on Rough Sets and Current Trends in Computing, Banff, Canada, 2000.
H. Selvaraj, H. Niewiadomski, M. Pleban, P. Sapiecha, Decomposition of Digital Circuits and Neural Networks, Proc. SCI 2001, US, 2001.
A. Skowron, C. Rauszer, The discemibility matrices and functions in information systems in: R. Slowinski (Ed.), Intelligent Decision Support. Handbook of Applications and Advances on the Rough Set Theory, Kluwer, 1992
C. Yang, V. Singhal, M. Ciesielski, BDD decomposition for efficient logic synthesis, International Conference on Computer Design, 1999.
W. Wan, M. Perkowski, A New Approach to the Decomposition of Incompletely Specified Multi-Output Function Based on Graph Coloring and Local Transformations and Its Application to FPGA Mapping, Proc. Euro-DAC’92.,1992.
D. de Werra, Heuristics for Graph Coloring, Computational Graph Theory, Tinhofer, Mayr, Noltenmeier, Syslo (Eds.), Springer-Verlag, New York, 1990.
http://www-ra.informatik.untuebingen.deSNNS/
B. Zupan, M. Bohanec, J. Demlar, I. Bratko, Feature transformation by function decomposition, IEEE Expert, Special Issue on Feature Transformation. 1997.
J. M. Zurada, Introduction to Artificial Neural Systems, West Publishing Company, St. Paul, 1992.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Buciak, P., Łuba, T., Niewiadomski, H., Pleban, M., Sapiecha, P., Selvaraj, H. (2003). Decomposition and Argument Reduction of Neural Networks. In: Rutkowski, L., Kacprzyk, J. (eds) Neural Networks and Soft Computing. Advances in Soft Computing, vol 19. Physica, Heidelberg. https://doi.org/10.1007/978-3-7908-1902-1_125
Download citation
DOI: https://doi.org/10.1007/978-3-7908-1902-1_125
Publisher Name: Physica, Heidelberg
Print ISBN: 978-3-7908-0005-0
Online ISBN: 978-3-7908-1902-1
eBook Packages: Springer Book Archive