DOI QR코드

DOI QR Code

Improvement of Pattern Recognition Capacity of the Fuzzy ART with the Variable Learning

가변 학습을 적용한 퍼지 ART 신경망의 패턴 인식 능력 향상

  • 이창주 (동양미래대학교 정보통신과) ;
  • 손병희 (동양미래대학교 정보통신과) ;
  • 홍희식 (동양미래대학교 정보통신과)
  • Received : 2013.09.09
  • Accepted : 2013.12.09
  • Published : 2013.12.31

Abstract

In this paper, we propose a new learning method using a variable learning to improve pattern recognition in the FCSR(Fast Commit Slow Recode) learning method of the Fuzzy ART. Traditional learning methods have used a fixed learning rate in updating weight vector(representative pattern). In the traditional method, the weight vector will be updated with a fixed learning rate regardless of the degree of similarity of the input pattern and the representative pattern in the category. In this case, the updated weight vector is greatly influenced from the input pattern where it is on the boundary of the category. Thus, in noisy environments, this method has a problem in increasing unnecessary categories and reducing pattern recognition capacity. In the proposed method, the lower similarity between the representative pattern and input pattern is, the lower input pattern contributes for updating weight vector. As a result, this results in suppressing the unnecessary category proliferation and improving pattern recognition capacity of the Fuzzy ART in noisy environments.

본 논문은 퍼지ART의 학습 방법의 하나인 FCSR(Fast Commit Slow Recode)에서 패턴 인식을 향상시키기 위해 가변 학습을 이용하는 새로운 학습방법을 제안하였다. 기존의 학습 방법은 연결 강도(대표패턴)의 갱신에 고정된 학습률이 사용된다. 이 방법은 같은 카테고리 내의 입력패턴과 대표패턴의 유사성의 정도와 관계없이 고정된 학습률로 연결 강도를 갱신한다. 이 경우 카테고리 경계에 있는 유사성이 낮은 입력패턴이 연결강도의 갱신에 크게 영향을 주게 된다. 따라서 잡음 환경에서 이것은 불필요한 카테고리 증식의 원인이 되고, 패턴 인식 능력을 낮추는 문제가 된다. 제안된 방법에서는 대표 패턴과 입력 패턴 사이에 유사성이 적을수록 연결강도의 갱신에 입력패턴의 기여를 낮추어간다. 그 결과 잡음환경에서 퍼지 ART의 불필요한 카테고리 증식을 억제하였고, 패턴 인식 능력을 향상시켰다.

Keywords

References

  1. G. A. Carpenter and S. Grossberg, "A massively parallel architecture for a self-organizing neural pattern recognition machine," Comput. Vision, Graphics, Image Process., vol. 37, no. 1, pp. 54-115, Jan. 1987. https://doi.org/10.1016/S0734-189X(87)80014-2
  2. G. A. Carpenter, S. Grossberg, and D. B. Rosen, "Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system," Neural Networks, vol. 4, no. 6, pp. 759-771, Dec. 1991. https://doi.org/10.1016/0893-6080(91)90056-B
  3. G. A. Carpenter and M. N. Gjaja, "Fuzzy ART choice functions," in Proc. World Congr. Neural Networks (WCNN), pp. 713-722, San Diego, U.S.A., June 1994.
  4. C. J. Lee, S. Y. Lee, and C. W. Lee, "Improvement of noise tolerance in fuzzy ART using a weighted sum and a fuzzy AND operation," IEICE Trans. Fundamentals Electron., Commun., Comput. Sci., vol. E78-A, no. 10, pp. 1432-1434, Oct. 1995.
  5. C. J. Lee, S. Y. Lee, and C. W. Lee, "A study on the new learning method to improve noise tolerance in fuzzy ART," J. Inst. Electron. Eng. Korea (IEEK), vol. 32-B, no. 10, pp. 112-117, Oct. 1995.
  6. C. J. Lee, C. G. Yoon, and C. W. Lee "A new learning method to improve category proliferation problem in fuzzy ART," in Proc. IEEE Int. Conf. Neural Network, vol. 3, pp. 1393-1396, Perth, Australia, Nov. 1995.
  7. J. S. Lee, C. J. Lee, and C. W. Lee, "Improvement of fuzzy ARTMAP performance in noisy input environment using weighted-average learning," IEICE Trans. Fundamentals Electron., Commun., Comput. Sci., vol. E80-A, no. 5, pp. 932-935, May 1997.
  8. J. S. Lee, C. G. Yoon, and C. W. Lee, "New learning method for fuzzy ARTMAP in the noise environment," IEE Electron. Lett., vol. 34, no. 1, pp. 95-97, Mar. 1998. https://doi.org/10.1049/el:19980004
  9. J. S. Lee, C. J. Lee, and C. W. Lee, "Improvement of recognition performance for fuzzy ARTMAP using average learning and slow learning," IEICE Trans. Fundamentals Electron., Commun., Comput. Sci., vol. E81-A, no. 3, pp. 514-516, Mar. 1998.
  10. J. Lee, "Fuzzy-ARTMAP based multi-user detection," J. Korea Inform. Commun. Soc. (KICS), vol. 37A no. 3, pp. 172-178. Mar. 2012. https://doi.org/10.7840/KICS.2012.37A.3.172
  11. C. J. Lee, B. H. Son "A study on the improvement of the noise adaptability for fuzzy ART using a variable learning rate," in Proc. Workshop Image Process. Image Understanding (IPIU), P-104, Jeju Island, Korea, Feb. 2012.