Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

Improved algorithm for learning speed by using the slope of activation function

활성화함수의 기울기를 이용한 수렴속도 개선 알고리듬

  • Kim, D.K. (Dept. of Electronics Engineering, Kang Weon National Univ) ;
  • Lee, S.H. (Dept. of Electronics Engineering, Kang Weon National Univ) ;
  • Kim, B.S. (Dept. of Computer Science, Hallym Univ.) ;
  • Kwon, H.Y. (Dept. of Electronics Engineering, Kang Weon National Univ)
  • 김대극 (강원대학교 전자공학과) ;
  • 이상희 (강원대학교 전자공학과) ;
  • 김백섭 (한림대학교 전자계산학과) ;
  • 권호열 (강원대학교 전자공학과)
  • Published : 1992.07.23
Download PDF
⟨ Previous Next ⟩

Abstract

Although the back-propagation(BP) algorithm is widely used for its simple structure and easy learning method, it has a drawback of slow convergence rate. In this paper, we propose an algorithm to improve this problem by manipulating the slope parameter of the activation function. The steepest descent method is used in learning the slope parameter, as in the case of weight. The simulation shows that the learning rates of the proposed algorithm is faster than the conventional BP algorithm.

Keywords