Title :
Noise corrupted pattern retrieval capability for sparsely encoded associative memory
Author :
Huang, Yo-Ping ; Gustafson, Donald
Author_Institution :
Dept. of Comput. Sci. & Eng., Tatung Inst. of Technol., Taipei, Taiwan
Abstract :
An efficient algorithm for retrieving noise corrupted patterns from an associative memory is presented. In any stable system, an input pattern with b bits differing from the nearest pattern is shown to be asynchronously attracted to that desired pattern in at most b steps. The proposed method is suitable for the sparse system and good for any associative memory. Examples are given to demonstrate the applicability and efficiency of the proposed method
Keywords :
content-addressable storage; neural nets; pattern recognition; neural nets; noise corrupted pattern retrieval; sparse system; sparsely encoded associative memory; Associative memory; Computer science; Encoding; Hamming distance; Neural networks; Neurons; Probes; Symmetric matrices; System performance;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298702
