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

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 연구는 2011학년도 동양미래대학교 학술 연구비 지원으로 수행되었습니다.First

Improvement of Properties of the Fuzzy ART with the Variable Weighed Average Learning

“…경계 범위의 테스트: [2][3][4][5][6][7][8][9][10] . 노드 J가 이미 한 번 이상 선택된 경우 기존 방식의 연결강도벡터 갱신에 식 (6)을 사용한다 [2][3][4][5][6][7][8][9][10] .…”

“…    대표패턴의 갱신에 반영한다 [10] . 즉 대표패턴과 입력 패턴의 거리가 멀수록 입력패턴이 대표패턴의 갱신에 참여하는 비율을 적게 하여 과도한 학습을 억제한다 [10] .…”