The use ofn-tuple or weightless neural networks as pattern recognition devices has been well documented [1]. They have a significant advantages over more common networks paradigms, such as the multi-layer perceptron in that they can be easily implemented in digital hardware using standard random access memories. To date,n-tuple networks have predominantly been used as fast pattern classification devices. The paper describes hown-tuple techniques can be used in the hardware implementation of a general auto-associative network.