Browse > Article
http://dx.doi.org/10.6109/jkiice.2011.15.7.1457

Setting Method of Competitive Layer using Fuzzy Control Method for Enhanced Counterpropagation Algorithm  

Kim, Kwang-Baek (신라대학교 컴퓨터공학과)
Publication Information
Journal of the Korea Institute of Information and Communication Engineering / v.15, no.7, 2011 , pp. 1457-1464 More about this Journal
Abstract
In this paper, we go one step further in that the number of competitive layers is not determined by experience but can be determined by fuzzy control rules based on input pattern information. In our method, we design a set of membership functions and corresponding rules and used Max-Min reasoning proposed by Mamdani. Also, we use centroid method as a defuzzification. In experiment that has various patterns of English inputs, this new method works beautifully to determine the number of competitive layers and also efficient in overall accuracy as a result.
Keywords
Competitive Layer; Fuzzy Control Method; Max_Min Reasoning; Defuzzification;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 P. D. Wasserman, Neural Computing Theory and Practice, Van Nostrand Reinhold, 1989.
2 조병래, 박경숙, 정환묵, "다중연결 Belief Network에 서의 동적 추론을 위한 카운터프로퍼게이션네트워 크," 한국정보과학회논문지, 제21권 제2호(A), pp.776-779, 1994.
3 김광백, "효과적인 패턴 인식을 위한 개선된 Counterpropagation 알고리즘," 한국해양정보통신학회논문지, 제12권, 9호, pp.16822-1688, 2008.
4 K. B. Kim, Abhijit S. Pandya, "Color Image Vector Quantization Using an Enhanced Self-Organizing Neural Network," Lecture Notes in Computer Science, LNCS 3314, Springer, pp.1121-1126, 2004.
5 김광백, 박충식, "퍼지 제어 시스템을 이용한 학습률 자동 조정 방법에 의한 개선된 역전파 알고리즘", 한국해양정보통신학회논문지, 제8권, 2호, pp.464-470, 2004.
6 정형환, 허동렬, 김상효, "신경회로망을 이용한 SVC 계통의 안정화에 관한 연구", 한국조명전기설비학회, 조명전기설비학회논문지, 제14권, 제3호, pp. 49-58, 2000.