Soft Computing in Hardware Implementations
Several VLSI implementations for soft computing are described, including piecewise approximation and nonlinear signal processing using MOS device characteristics. Both fuzzy and neural technologies are investigated. Fuzzy controllers are the most popular choice for hardware implementation of complex control surfaces because they are easy to design. Neural controllers are more complex and hard to train, but provide an outstanding control surface with much less error than that of a fuzzy controller.
KeywordsMembership Function Fuzzy Controller Soft Computing Control Surface Very Large Scale Integration
Unable to display preview. Download preview PDF.
- 1.Zurada, J., Introduction to Artificial Neural Systems, West Publishing Company, 1992.Google Scholar
- 2.Wilamowski B. M. (1998) “Neuro-Fuzzy Systems and its applications” tutorial at 24th IEEE International Industrial Electronics Conference (IECON’98) August 31 - September 4, 1998, Aachen, Germany, vol. 1, pp. t35-t49.Google Scholar
- 3.Wilamowski, B. M., “Neural Networks and Fuzzy Systems” The Mechatronics Handbook. CRC Press 2002, pp. 32–1 to 32–26Google Scholar
- 5.Rodriguez-Vazquez A. and F. Vidal-Verdu, Learning in Neuro/Fuzzy Analog Chips, IEEE International Symposium on Circuits and Systems, Seattle WA, vol. 3, pp. 2325–2328, April 30-May 3 1995.Google Scholar
- 8.Ahmadi S., L. Sellami, and R. W. Newcomb, A CMOS PWL Fuzzy Membership Function, IEEE International Symposium on Circuits and Systems, Seattle WA, vol. 3, pp. 2321–2324, April 30-May 3 1995Google Scholar
- 9.Angulo J.R., (1995) A BiCMOS Universal Membership Function Circuit with Fully Independent, Adjustable Parameters, Proc. IEEE International Symposium on Circuits and Systems, pp. 275–278.Google Scholar
- 10.Baturone I., A. Barriga, and J. L. Huertas, “Multi-input Voltage and Current-Mode Min/Max Circuits,” Proceedings: 3rd Int. Conf. on Fuzzy Logic, Neural Networks and Soft Computing, Iizuka, Japan, 1994.Google Scholar
- 11.Ota Y. and B. Wilamowski, Current-Mode CMOS Implementation of a Fuzzy Min-Max Network, World Congress on Neural Nerworks vol. II, pp. 480–483, 1995.Google Scholar
- 13.Wilamowski B.M. and J. Binfet, “Do Fuzzy Controllers Have Advantages over Neural Controllers in Microprocessor Implementation” Proc. of. 2-nd International Conference on Recent Advances in Mechatronics–ICRAM’99, Istanbul, Turkey, pp. 342–347, May 24–26, 1999.Google Scholar