The objective of this work is to use a generalized regression neural network (GRNN) in the design of extended-release aspirin tablets. As model formulations, 10 kinds of aspirin matrix tablets were prepared. Eudragit RS PO was used as matrix substance. The amount of Eudragit RS PO and compression pressure were selected as causal factors. In-vitro dissolution-time profiles at four different sampling times, as well as coefficients n (release order) and log k (release constant) from the Peppas equation were estimated as release parameters. A set of release parameters and causal factors were used as tutorial data for the GRNN and analyzing using a computer. A GRNN model was constructed. The optimized GRNN model was used for prediction of formulation with desired in vitro drug release. For two tested formulations there was very good agreement between the GRNN predicted and observed in vitro profiles and estimated coefficients. Calculated difference (f(1)) and similarity (f(2)) factors indicate that there is no difference between predicted and experimental observed drug release profiles. This work illustrates the potential for an artificial neural network, GRNN, to assist in development of extended-release dosage forms. This method can be employed to achieve a desired in vitro dissolution profile.