Using Xilinx FPGAs to implement neural networks and fuzzy systems

Over the last thirty years, since Zadeh first introduced fuzzy set theory, there has been widespread interest in the real-time application of fuzzy logic, particularly in the area of control. Recently, there has been considerable interest in the development of dedicated hardware implementations which facilitate high speed processing. However, the main drawback of such an approach is that it is only cost effective for high-volume applications. A more feasible methodology for lower volume problems demands the application of general-purpose or programmable hardware such as the Xilinx FPGAs. There has been a similar trend in the area of neural networks, as initial research employed software simulations but more recent interest has investigated hardware implementations. FPGAs are becoming increasingly popular for prototyping and designing complex hardware systems. The structure of an FPGA can be described as an "array of blocks" connected together via programmable interconnections. The main advantage of FPGAs is the flexibility that they afford. An engineer can change and refine a device's design by exploiting the device's reprogrammability. Xilinx introduced the world's first FPGA, the XC2064, in 1985. This contained approximately 1000 logic gates. Since then, the gate density of Xilinx FPGAs has increased 25 times. There has been a lot of recent interest in the FPGA realisation of fuzzy systems. Similarly there are a number of FPGA implementations of neural networks reported in the literature. However. this paper provides a report on the implementation of both architectures and also offers a comparison with the hybrid structure.