Title :
The capacity of associative memory by using r-order shifting rules
Author :
Kuo, I. Chuan ; Zhang, Zhen
Author_Institution :
Commun. Sci. Inst., Univ. of Southern California, Los Angeles, CA, USA
Abstract :
The second-order Hopfield associative memory has storage capacity of order O(n/log n), if the stored vectors and probe vector are subject to uniform distributions. Unfortunately, this is not always the case practically. We prove that the capacity drops to order of zero when stored vectors and probe vector have nonuniform distributions. Therefore, it is necessary to use the "shifting" method in the modified Hopfield model to improve the storage capacity, where "shifting" means subtracting means from vectors. The influence of probability distribution on capacity is expressed
Keywords :
Hopfield neural nets; content-addressable storage; associative memory capacity; nonuniform distributions; probability distribution; probe vector; r-order shifting rules; second-order Hopfield associative memory; shifting method; storage capacity; stored vectors; Associative memory; Capacity planning; Equations; Probability distribution; Probes;
Conference_Titel :
Systems, Man, and Cybernetics, 1994. Humans, Information and Technology., 1994 IEEE International Conference on
Conference_Location :
San Antonio, TX
Print_ISBN :
0-7803-2129-4
DOI :
10.1109/ICSMC.1994.400239
