Title :
The capacity of associative memory by using a combination rule
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). To improve the capacity of associative memory, a new storage and retrieval algorithm is proposed. The transformation of a tensor into a vector is an important part of the method
Keywords :
Hopfield neural nets; content-addressable storage; associative memory capacity; combination rule; retrieval algorithm; second-order Hopfield associative memory; storage algorithm; tensor transformation; Associative memory; Information theory; Least squares approximation; Least squares methods; Neural networks; Optical computing; Optical fiber networks; Polynomials; Probes; Tensile stress;
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.1994.400240
