Title :
Character recognition in a sparse distributed memory
Author :
Hong, Young-Sik ; Chen, Su-Shing
Author_Institution :
Dept. of Comput. Sci., Dongguk Univ., Seoul, South Korea
Abstract :
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
Keywords :
character recognition; content-addressable storage; access distance; address decoding; character recognition; model; pattern retrieval; sparse distributed memory; Character generation; Character recognition; Computer science; Decoding; Information retrieval; Mathematical model; Neurons; Pattern recognition; Read-write memory; Testing;
Journal_Title :
Systems, Man and Cybernetics, IEEE Transactions on
