The Convergent Rates of Estimation of Conditional Quantiles Using Artificial Neural

In this paper, we give the mean square convergence rates of conditional quantile estimators based on single hidden layer feed forward networks. Our results are formulated both for independent identically distributed （i.i.d.） random variables and for stationary mixing processes （α-mixing and β-mixing）. It turns out that the rates are the same as those for regression using neural networks. We use the same techniques as in Zhang （1998）.