Title :
A study of neural network model with importance emphasizing for associative memory
Author :
Yu, Dao-heng ; Yu, Xiang ; Mori, Shinsaku
Author_Institution :
Dept. of Electr. Eng., Keio Univ., Yokohama, Japan
Abstract :
This paper shows by a great number of computer modelling results that the capacity of associative memory and recall probability (recalling Chinese with 40% noise) of the new network is much better than Hopfield´s. It can also be better than Y.C. Lee´s higher order correlation network if a larger emphasizing parameter P is used
Keywords :
content-addressable storage; neural nets; Chinese; associative memory; capacity; higher order correlation network; importance-emphasizing model; neural network model; recall probability; Associative memory; Automation; Computational modeling; Computer networks; Computer simulation; Equations; Hardware; Lyapunov method; Magnetooptic recording; Neural networks;
Conference_Titel :
Singapore ICCS/ISITA '92. 'Communications on the Move'
Print_ISBN :
0-7803-0803-4
DOI :
10.1109/ICCS.1992.255058
