Title :
Unifying the Hopfield and Hamming binary associative memories
Author :
Houselander, P. ; Taylor, J.T.
Author_Institution :
Dept. of Elctron. & Electr. Eng., Univ. College, London, UK
Abstract :
A mathematical technique that makes it possible to calculate the capacity (which is defined) of an associative memory is introduced. The technique is used to investigate the performance (in terms of capacity) of the original Hopfield network and some novel derivatives. Through a logical sequence of structural improvements, it is shown that a natural conclusion to the extension of the Hopfield network is the Hamming network. This network exhibits the theoretical maximum capacity obtainable from an associative memory structure
Keywords :
content-addressable storage; memory architecture; neural nets; self-organising storage; CAM; Hamming network; Hopfield network; artificial neural networks; binary associative memories; mathematical technique; memory capacity calculation; Artificial neural networks; Associative memory; Educational institutions; Equations; Error correction; Facsimile; Hamming distance; Probes;
Conference_Titel :
Circuits and Systems, 1990., IEEE International Symposium on
Conference_Location :
New Orleans, LA
DOI :
10.1109/ISCAS.1990.111962
