Title :
Associative ability of higher order neural networks
Author :
Yatsuki, Shuji ; Miyajima, Hiromi
Author_Institution :
Dept. of Electr. Eng., Kagoshima Univ., Japan
Abstract :
Higher order neural networks (HONNs) have been proposed as new systems. In this paper, we show some theoretical results on the associative ability of HONNs. Memory capacity of HONNs is much larger than that of the conventional neural networks. The capacity of auto-correlation associative memory is (mk)/(2 log m), where m is the number of neurons and K is the order of connections
Keywords :
associative processing; content-addressable storage; neural nets; associative ability; auto-correlation associative memory; higher order neural networks; memory capacity; Associative memory; Autocorrelation; Input variables; Neural networks; Neurons; Pattern recognition;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616222
