Title :
Improving the Hamming binary associative memory
fDate :
5/24/1990 12:00:00 AM
Abstract :
The Hamming network is a binary associative memory which exhibits the maximum theoretically obtainable performance in terms of capacity and associativity. The structure is not ideal and two modifications which reduce the number of connections in the correlation matrix and in the selection layers are suggested. These modifications offer a significant reduction in the number of calculations required.
Keywords :
content-addressable storage; neural nets; Hamming binary associative memory; Hamming network; associativity; capacity; connection number reduction; correlation matrix; maximum theoretically obtainable performance; modifications; neural networks improvement; selection layers;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19900460
