DocumentCode :
423638
Title :
Higher order differential correlation associative memory of sequential patterns
Author :
Miyajima, Hiromi ; Shigei, Noritaka ; Hamakawa, Yasuo
Author_Institution :
Dept. of Electr. & Electron. Eng., Kagoshima Univ., Japan
Volume :
2
fYear :
2004
fDate :
25-29 July 2004
Firstpage :
891
Abstract :
This paper describes some properties of storage capacity and robustness of differential correlation associative memory of sequential patterns using higher order neural networks. First, it is shown that storage capacities for k=1, 2 and 3 dimensional cases are 0.059N, 0.023(2N) and 0.014(3N) from the prediction using the transition properties, respectively, where N is the number of neurons and (KN) means the combination of k from N. And it is shown that higher order models are superior in the pattern selection ability to the conventional one. Further, it is shown that higher order differential correlation models have high robustness compared to the conventional correlation models.
Keywords :
content-addressable storage; correlation methods; neural nets; pattern recognition; associative memory; higher order differential correlation model; neural networks; numerical simulation; sequential pattern selection; storage capacity; transition properties; Associative memory; Biological neural networks; Brain modeling; Computer networks; Input variables; Neural networks; Neurons; Predictive models; Robustness;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
ISSN :
1098-7576
Print_ISBN :
0-7803-8359-1
Type :
conf
DOI :
10.1109/IJCNN.2004.1380048
Filename :
1380048
Link To Document :
بازگشت