BOUNDEDNESS OF WEIGHTED COEFFICIENTS OF PERCEPTRON LEARNING ALGORITHM AND GLOBAL CONVERGENCE OF FIXED POINT AND LIMIT CYCLE BEHAVIORS
In this paper, a condition for the boundedness of weighted coefficients of the perceptron with arbitrary initial weights and an arbitrary set of bounded training feature vectors is given and proved. Based on this derived condition, conditions for the global convergence of the output of the perceptron with a set of nonlinearly separable bounded training feature vectors to limit cycles are given and proved, and the maximum number of updates of the weighted coefficients of the perceptron before the output of the perceptron reaches the limit cycles is given. Finally, the perceptron with periodically time varying weighted coefficients is investigated. An ∞ H optimization approach is proposed for the design of this perceptron. Numerical computer simulation results show that the perceptron with periodically time varying weighted coefficients could achieve better recognition performances compared to that with only one set of weighted coefficients.
Charlotte Yuk-Fan Ho Bingo Wing-Kuen Ling Hak-Keung Lam Muhammad H U Nasir
Dept. of Electronic Engineering and School of Mathematical Sciences, Queen Mary,University of London Dept. of Electronic Engineering, Division of Engineering, Kings College London, Strand, London,WC2R Dept. of Electronic Engineering, Division of Engineering, Kings College London, Strand. London, WC2
国际会议
杭州
英文
58-63
2007-06-06（万方平台首次上网日期，不代表论文的发表时间）