Abstract
This study is concerned with cascade architectures of fuzzy neural networks. These networks exhibit three interesting and practically appealing features: (i) come with sound and transparent logic characteristics by being developed with the aid of AND and OR fuzzy neurons and subsequently logic processors (LPs), (ii) possess significant learning abilities and in this way fall in the realm of neuro-fuzzy architectures, and (iii) exhibit an evident hierarchical structure owing to the cascade of the LPs. We discuss main functional properties of the model and relate them to its form of cascade-type of systems formed as a stack of LPs. The construction of the systems of this form calls for some structural optimization that is realized in the realm of genetic optimization. The structure of the network that deals with a selection of a subset of input variables and their distribution across the individual LPs is optimized with the use of genetic algorithms (GAs). The chromosomes encode the order of the variables as well as include the parameters (connections) of the neurons. We discuss various schemes of genetic optimization (both a two-level and single-level GA) and gradient-based learning aimed at further refinement of the connections of the neurons. We elaborate on the interpretation aspects of the network and show how this leads to a Boolean or multivalued logic description of the experimental data. A number of numeric data sets are discussed with respect to the performance of the constructed networks and their interpretability.
Article PDF
We’re sorry, something doesn't seem to be working properly.
Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.
References
Abelson, H., et al. (1982). ''Compositional Complexity of Boolean Functions,'' Discrete Applied Mathematics 4, 1–10.
Babuska, R. (1998). Fuzzy Modeling for Control. Norwell, MA: Kluwer Academic Publishers.
Bargiela, A. and W. Pedrycz. (2002). Granular Computing: An Introduction. Dordrecht: Kluwer Academic Publishers.
Boros, E., et al. (1995). ''Decomposability of Partially Defined Boolean Functions,'' Discrete Applied Mathematics, 62, 51–75.
Chung, F. L. and J. C. Duan. (2000). ''On Multistage Fuzzy Neural Network Modeling,'' IEEE Transactions on Fuzzy Systems 8, 125–142.
Duan, J. C. and F. L. Chung. (2002). ''Multilevel Fuzzy Relational Systems: Structure and Identification,'' Soft Computing 6, 73–86.
Ekin, O., P. L. Hammer, and A. Kogan. (2000). ''Convexity and Logical Analysis of Data,'' Theoretical Computer Science 244, 95–116.
Goldberg, D. E. (1989). Genetic Algorithms in Search, Optimization and Machine Learning. New York: Addison-Wesley.
Lanchares, J., J. I. Hildago, and J. M. Sanchez. (1997). ''Boolean Networks Decomposition Using Genetic Algorithms,'' Microelectronics Journal 28, 551–560.
Michalewicz, Z. (1996). Genetic Algorithm+Data Structures=Evolution Programs. 3rd Edition Berlin: Springer Verlag.
Mitaim, S. and B. Kosko. (2001). ''The Shape of Fuzzy Sets in Adaptive Function Approximation,'' IEEE Transactions on Fuzzy Systems 9(4), 647–656.
Ono, H., K. Makino, and T. Lbaraki. (2002). ''Logical Analysis of Data with Decomposable Structures,'' Theoretical Computer Science, in Press.
Pedrycz, W. (1993). ''Fuzzy Neural Networks and Neurocomputations,'' Fuzzy Sets and Systems 56, 1–28.
Pedrycz, W. and J. Valente de Oliveira. (1996). ''An Algorithmic Framework for Development and Optimization of Fuzzy Models,'' Fuzzy Sets and Systems, 80, 37–55.
Perkowski, M. A. and J. E. Brown. (1988). ''A Unified Approach to Designs Implemented with Multiplexers to the Decomposition of Boolean Functions,'' Proceedings of ASEE Annual Conference, pp. 1610-1618.
Rose, J., A. El Gamal, and A. Sangiovanni-Vincentelli. (1993). ''Architecture on FPGA,'' Proceedings of the IEEE, July, 1013-1029.
Rovatti, R., R. Guerrieri, and G. Baccarani. (1995). ''An Enhanced Two-Level Boolean Synthesis Methodology for Fuzzy Rules Minimization,'' IEEE Transactions on Fuzzy Systems 3, 288–299.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Pedrycz, W., Reformat, M. & Han, C. Cascade Architectures of Fuzzy Neural Networks. Fuzzy Optimization and Decision Making 3, 5–37 (2004). https://doi.org/10.1023/B:FODM.0000013070.26870.e6
Issue Date:
DOI: https://doi.org/10.1023/B:FODM.0000013070.26870.e6