Browsing by Author "SIU, S"

Now showing 1 - 3 of 3

L(P) NORM BACK-PROPAGATION ALGORITHM FOR ADAPTIVE EQUALIZATION
(1995-09-01)
SIU, S
;
CHANG, CH
;
WEI, CH
;
電子工程學系及電子研究所
;
Department of Electronics Engineering and Institute of Electronics
The l(p) norm back propagation algorithm for perceptron based adaptive equalization is analyzed taking account of possible numerical problem encountered when p < 1. Two methods are proposed to overcome the numerical problem. Computer simulations indicate that simultaneous improvement in convergence rate and bit-error-rate (BER) performance can be achieved by using p < 2.
L(P) NORM BACK-PROPAGATION ALGORITHM FOR ADAPTIVE EQUALIZATION
(1995-09-01)
SIU, S
;
CHANG, CH
;
WEI, CH
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The l(p) norm back propagation algorithm for perceptron based adaptive equalization is analyzed taking account of possible numerical problem encountered when p < 1. Two methods are proposed to overcome the numerical problem. Computer simulations indicate that simultaneous improvement in convergence rate and bit-error-rate (BER) performance can be achieved by using p < 2.
ON THE CONVERGENCE OF THE L(P)-NORM ALGORITHM FOR POLYNOMIAL PERCEPTRON HAVING DIFFERENT ERROR SIGNAL DISTRIBUTIONS
(1995-03-01)
CHANG, CH
;
SIU, S
;
WEI, CH
;
電控工程研究所
;
Institute of Electrical and Control Engineering
The convergence property of the l(p)-norm algorithm for polynomial-perceptron having different error signal distributions will be analyzed in this paper. To see the effect of error signal on the convergence rate, two types of activation functions are considered in the analysis: one is of a linear type and the other is of a sigmoidal type. Different activation functions yield different ranges of output signal and, in turn, yield different error signal distributions. Linear activation function causes the error signal to be distributed in an uncertain way, while sigmoidal activation function causes it to be distributed in a tightly bounded region. Based on this difference the convergence property of the l(p)-norm algorithm, 1 less than or equal to p less than or equal to 2, is investigated in this paper. Expressions of average learning gains are obtained in terms of the power metric p, the error probability, and the upper bound bf the error signal distribution. Analytic results indicate that it is of particular value in using the l(p)-norm algorithm for the perceptron using sigmoidal activation functions. Computer simulation of an adaptive equalizer using this algorithm confirms the theoretical analysis.