Abstract
In this study, a model on the basis of artificial neural networks is developed to predict the peak horizontal acceleration. The neural network model provides an objective analysis method which requires neither specifying predictive functional forms nor the independence of the inside variables. The Joyner and Boore data set (DSSA, Vol. 71, pp. 2011-2038, 1981), was used for analysis. For comparison, one-and two-step regression procedures were also applied to the same data set. Various fitness criteria have been considered. Finally, the proposed procedure showed an agreeable capability for the required prediction of ground motion parameters.
