Ch. Chang et al., A POLYNOMIAL-PERCEPTRON BASED DECISION-FEEDBACK EQUALIZER WITH A ROBUST LEARNING ALGORITHM, Signal processing, 47(2), 1995, pp. 145-158
A new equalization scheme, including a decision feedback equalizer (DF
E) equipped with polynomial-perceptron model of nonlinearities and a r
obust learning algorithm using l(p)-norm error criterion with p < 2, i
s presented in this paper, This equalizer exerts the benefit of using
a DFE and achieves the required nonlinearities in a single-layer net.
This makes it easier to train by a stochastic gradient algorithm in co
mparison with a multi-layer net. The algorithm is robust to aberrant n
oise for the addressed equalizer and, hence, converges much faster in
comparison with the l(p)-norm. A detailed performance analysis conside
ring possible numerical problem for p < 1 is given in this paper. Comp
uter simulations show that the scheme has faster convergence rate and
satisfactory bit error rate (BER) performance. It also shows that the
new equalizer is capable of approaching the performance achieved by a
minimum EER equalizer.