Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Learning Method of the ADALINE Using the Fuzzy System

퍼지 시스템을 이용한 ADALINE의 학습 방식

  • Published : 2003.01.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we proposed a learning algorithm for the ADALINE network. The proposed algorithm exploits fuzzy system for automatic tuning of the weight parameters of the ADALINE network. The inputs of the fuzzy system are error and change of error, and the output is the weight variation. We used different scaling factor for each weights. In order to verify the effectiveness of the proposed algorithm, we peformed the simulation and experimentation for the cases of the noise cancellation and the inverted pendulum control. The results show that the proposed algorithm does not need the learning rate and improves 4he performance compared to the Widrow-Hoff delta rule for ADALINE.

본 논문에서는 ADALINE의 학습을 위한 알고리즘을 제안하였다. 제안한 알고리즘은 직접 퍼지 논리 시스템을 이용하여 ADALINE의 연결강도를 조정하는 방식으로 퍼지 논리 시스템의 입력은 오차와 오차의 변화분이고, 출력은 연결강도 변화분이며, 각각의 연결강도는 스케일링 팩터만 다르게 하여 사용하였다. 제안한 알고리즘의 유용성을 확인하기 위하여 노이즈 제거와 인버티드 펜들럼 제어에 대하여 시뮬레이션과 실험을 수행하였다. Widrow-Hoff의 델타 규칙과 비교하였을 때 제안한 방식은 학습율을 선택할 필요도 없고, 성능이 우수함을 확인하였다.

Keywords

References

  1. Ling Zhang, Bo Zhang, 'A geometrical representation of McCulloch-Pitts neural model and its applications,' IEEE Transactions on Neural .Networks, vol. 10, pp. 925-929, 1999 https://doi.org/10.1109/72.774263
  2. Simon Haykin, Neural network a comprehensive foundation, second edition, Prentice-Hall, 1999
  3. Hayman. S, 'The McCulloch-Pitts model,' IJCNN '99. International Joint Conference on Neural Networks, vol. 6, pp. 4438-4439, 1999 https://doi.org/10.1109/IJCNN.1999.830886
  4. Bernard Widrow, Michael A Lehr, '30 Years of adaptive Neural Networks: Perceptron, Madaline, Backpropagation,' Proceedings of the IEEE, vol. 78, no, 9, PP. 1415-1442, 1990 https://doi.org/10.1109/5.58323
  5. Zi-Qin, Michael T. Manry, Jeffrey L. Schiano, 'LMS Learning Algorithms: Misconceptions and New Results on Convergence,' IEEE Transactions on Neural Netoworks, vol, 11, no. 1, 2000 https://doi.org/10.1109/72.822509
  6. Li-Xin Wang, A course in fuzzy systems and control, Prentice Hall PTR Prentice-Hall Inc., 1997
  7. Kevin M. Passino, Stephen Yurkovich, Fuzzy control, Addison-Wesley, 1997
  8. Rodney Winter, Bernard Widrmv, 'Madaline Rule II : A Training Algorithm for Neural Networks', IEEE International Conference on Neural Networks, pp. 401-408, vol. 1, 1988 https://doi.org/10.1109/ICNN.1988.23872
  9. Hagan, Demuth, Beale, NEURAL NETWORK DESIGN, PWS Publishing Company, 1996