The Adaptive Resonance Theory (ART) neural network is a novel method for the cell formation problem in group technology (GT). The advantages of using an ART network over other conventional methods are its fast computation and the outstanding ability to handle large scale industrial problems. One weakness of this approach is that the quality of a grouping solution is highly dependent on the initial disposition of the machine-part incidence matrix especially in the presence of bottleneck machines and/or bottleneck parts. The effort of this paper has been aimed at alleviating the above mentioned problem by the introduction of a set of supplementary procedures. The advantages of the supplementary procedures are demonstrated by 40 examples from the literature. The results clearly demonstrate that our algorithm is more reliable and efficient in cases of ill-structured data.