Browse > Article
http://dx.doi.org/10.6109/jkiice.2008.12.9.1682

An Enhanced Counterpropagation Algorithm for Effective Pattern Recognition  

Kim, Kwang-Baek (신라대학교 컴퓨터정보공학부)
Abstract
The Counterpropagation algorithm(CP) is a combination of Kohonen competition network as a hidden layer and the outstar structure of Grossberg as an output layer. CP has been used in many real applications for pattern matching, classification, data compression and statistical analysis since its learning speed is faster than other network models. However, due to the Kohonen layer's winner-takes-all strategy, it often causes instable learning and/or incorrect pattern classification when patterns are relatively diverse. Also, it is often criticized by the sensitivity of performance on the learning rate. In this paper, we propose an enhanced CP that has multiple Kohonen layers and dynamic controlling facility of learning rate using the frequency of winner neurons and the difference between input vector and the representative of winner neurons for stable learning and momentum learning for controlling weights of output links. A real world application experiment - pattern recognition from passport information - is designed for the performance evaluation of this enhanced CP and it shows that our proposed algorithm improves the conventional CP in learning and recognition performance.
Keywords
Counterpropagation; Kohonen Competition Network; Outstar Structure; Learning Rate; Momentum Learning;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Jacek M. Zurada, Artificial Neural Systems, West Publishing Company, 1992
2 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
3 권장우, 정인길,홍승홍, "시간 지연을 갖는 쌍전파 신경회로망을 이용한 근전도 신호인식에 관한 연구," 의공학회지, 17권, 3호, pp.395 -401, 1996
4 A. Mishenin, "Using Conter Propagation Neural Network for Building Intelligent Decision Supporting Systems," Computer Modelling and New Technologies, Vol.10, No.4, pp 66-69, 2006
5 K. B. Kim, Y. J. Kim, A. S. Oh, "An Intelligent System for Passport Recognition Using Enhanced RBF Network," Lecture Notes in Computer Science, LNCS 3314, Springer, pp.762-767, 2004
6 Peter J. Roberts, Rodney A. Walker, "Application of a Counterpropagation Network in Star Identification," Proceeding of AIAA Guidance, Navigarion and Control Conference, 2005
7 조병래, 박경숙, 정환묵, "다중연결 Belief Network에서의 동적 추론을 위한 카운터프로퍼게이션 네트워크," 한국정보과학회논문지, 제21권 제2호(A) pp.776-779, 1994