Abstract
In this paper a method of creating layers of feed-forward neural network that does not need to be learned is presented. Described approach is based on algorithms used in synthesis of logic circuits. Experimental results presented in the paper prove that this method may significantly decrease the time of learning process, increase generalization ability and decrease a probability of sticking in a local minimum. Further work and goals to achieve are also discussed.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Pawlak, Z.: Rough Sets: Theoretical Aspects of Reasoning About Data. Kluwer Academic Publishing, Dordrecht (1991)
Niewiadomski, H.: Serial decomposition of feedforward neural networks. Warsaw University of Technology. M. Sc. Thesis (2003)
Lewandowski, J., Rawski, M., Migacz, M., Rybiński, H.: Analysis of decomposition of feed-forward neural network and it’s impact on ability to generalization. Multimedia and network information systems. Oficyna Wydawnicza Politechniki Wrocławskiej, Wrocław, pp. 269–278 (2006)
Lewandowski, J.: Dekompozycja w sieciach neuronowych. Warsaw University of Technology, M. Sc Thesis (2006)
Haykin, S.: Neural Networks. A Comprehensive Foundation, 2nd edn. Pearson Education, Inc. Delhi, India (2005)
Osowski, S.: Sieci neuronowe do przetwarzania informacji. Oficyna Wydawnicza Politechniki Warszawskiej. Warszawa (2000)
Kasabov, N.K.: Foundations of Neural Networks, Fuzzy Systems, and Knowledge Engineering. Massachusetts Institute of Technology (1996)
Łuba, T., Selvaraj, H., Nowicka, M., Kraśniewski, A.: Balanced multilevel decomposition and its applications in FPGA-based synthesis. In: Saucier, G., Mingnotte, A. (eds.) Logic and Architecture Synthesis, Chapman & Hall, Sydney (1995)
Łuba, T., Lasocki, R., Rybnik, J.: An Implementation of Decomposition Algorithm and its Application in Information Systems Analysis and Logic Synthesis. In: Ziarko, W. (ed.) Rough Sets, Fuzzy Sets and Knowledge Discovery. Workshops in Computing Series, pp. 458–465. Springer, Heidelberg (1994)
Brzozowski, J.A., Łuba, T.: Decomposition of Boolean Functions Specified by Cubes. Journal of Multi-Valued Logic & Soft. Computing 9, 377–417 (2003)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lewandowski, J., Rawski, M., Rybinski, H. (2007). Application of Parallel Decomposition for Creation of Reduced Feed-Forward Neural Networks. In: Kryszkiewicz, M., Peters, J.F., Rybinski, H., Skowron, A. (eds) Rough Sets and Intelligent Systems Paradigms. RSEISP 2007. Lecture Notes in Computer Science(), vol 4585. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73451-2_59
Download citation
DOI: https://doi.org/10.1007/978-3-540-73451-2_59
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73450-5
Online ISBN: 978-3-540-73451-2
eBook Packages: Computer ScienceComputer Science (R0)