This paper introduces a neural network architecture called a fuzzy adaptiv Hamming net for pattern clustering. The fuzzy adaptive Hamming net derived from fuzzy ART, which can learn stable categories in response to botanalog and binary input patterns. This model allows new prototypes to be added to an existing set of memorized prototypes without retraining the entire network. Because the functional behavior of the fuzzy adaptive Hamming net is equivalent to that of fuzzy ART, some useful properties of fuzzy ART can be applied to the fuzzy adaptive Hamming net. In addition, the proposed network finds the appropriate category more efficiently than does fuzzy ART: for the same input sequences, the fuzzy adaptive Hamming net obtais the same recognition categories as does fuzzy ART without any searching. The fuzzy adaptive Hamming net not only improves the computational speed and efficiency of fuzzy ART, but is also easier to implement. With some modifications, the concepts of the fuzzy adaptive Hamming net can be applied to other ART-type models.