Character recognition in a sparse distributed memory

P. Kanerva's (1988) sparse distributed memory model is applied to character recognition. The results of recognizing corrupted characters, using a sparse distributed memory with fewer than 10000 locations, is described: 100 corrupted test patterns were generated to recognize 18 template patterns. The performance of the model is evaluated. Insights about the behavior of sparse distributed memories as well as the model's applicability to character recognition are provided. It was found that a sparse distributed memory of small size can recognize patterns with considerable noise.<
>