It is needless to say that a panoply of real-world applications of fuzzy sets call for a variety of systems realizing fuzzy computation. Concurrently, it is highly desirable to develop some universal computing modules that may be easily customized to meet required hardware — software specifications. This concept is not that new, as in two-valued logic we can easily encounter various categories of configurable and programmable devices (PLDs), ranging from PAL’s to FPGA’s. These devices are standardized general purpose logic units, which may be configured to perform specific functions. To follow a similar avenue, it is indispensable to identify a few generic processing modules that are complete enough, when considered from a functional point of view, for general computations with fuzzy linguistic variables. A family of logic-based neurons , emerges as a collection of processing operations whose role is to model logic-oriented processing dominant in the theory of fuzzy sets. These configurable architectures arising within this framework can directly cope with the topology of the problem at hand.
KeywordsFuzzy Neural Network Parametric Learning Memory Unit Triangular Norm Learn Unit
Unable to display preview. Download preview PDF.
- Pedrycz, W.,”Fuzzy neural networks and neurocomputations,” Fuzzy Sets and Systems, 56, pp. 1–28, 1993.Google Scholar
- Card, H. “Digital VLSI backpropagation networks”, Canadian J. Elect. & Comp. Eng., vol. 20, no. 1, pp. 15–23, 1995.Google Scholar
- Dickson, J., R. McLeod and H. Card, “Stochastic arithmetic implementations of artificial neural networks with in-situ learning”, Proc. IEEE Int. Conf. Neural Networks, (San Francisco, CA), pp. 711-716, 1993.Google Scholar
- Tomlinson Jr., M.S., DJ. Walker, and A. Sivilotti, “A digital neural network architecture for VLSI”, Proc. Int. Joint Conf. Neural Networks, (San Diego, CA), vol. 2, pp. 545–550, 1990.Google Scholar