A real-time neural network, AART1 (augmented adaptive resonance theory), that describes the dynamics of the ART1 model is presented. This involves modifying the architecture of the ART1 network through the addition of a reset node and a set of inhibitory nodes in the F2 layer. Along with modifications to the differential equations describing the F1 and F2 layer nodes, these changes embody the functionality of the orienting subsystem in the ART1 model. In addition, the modifications described here allow the ART1 model to be implemented solely using a set of concurrently executing nonlinear differential equations. Thus, the AART1 network requires no external control features. Computer simulation results demonstrate the efficacy of this network.