Title :
Auto correlation associative memory by Universal Learning Networks (ULNs)
Author :
Shibuta, Keiko ; Hirasawa, Kotaro ; Hu, Jinglu ; Murata, Junichi
Author_Institution :
Graduate Sch. of Inf. Sci & Electr. Eng.., Kyushu Univ., Japan
Abstract :
In this paper, we propose a new auto correlation associative memory using Universal Learning Networks (ULNs). It enables not only to obtain associative memory by optimizing parameters but also to store more memories than conventional models by introducing "don\´t care nodes" or "sensitivity term". This is expected to settle some problems related to associative memory.
Keywords :
content-addressable storage; learning (artificial intelligence); neural nets; recurrent neural nets; RasID; ULNs; Universal Learning Networks; associative memory; auto correlation associative memory; Associative memory; Autocorrelation; Biological neural networks; Brain modeling; Computer simulation; Control system synthesis; Delay effects; Gold; Neural networks; Neurons;
Conference_Titel :
SICE 2002. Proceedings of the 41st SICE Annual Conference
Print_ISBN :
0-7803-7631-5
DOI :
10.1109/SICE.2002.1195251
