Title :
Associative memory of gray-scale images based on chaotic neural networks
Author :
Li, Ke ; Yang, Luxi ; Liu, Ju ; He, Zhenya
Author_Institution :
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Abstract :
We propose a novel correlative learning rule for multi-value patterns, considering that conventional associative memory system processes only binary ones. Successful memory and recognition were achieved on the bases of a modified globally coupled map model (S-GCM) with the proposed method. An analysis of the recognition results and factors are also given
Keywords :
chaos; content-addressable storage; image recognition; learning (artificial intelligence); neural nets; associative memory system; chaotic neural networks; correlative learning rule; gray-scale images; image recognition results; modified globally coupled map model; multi-value patterns; Associative memory; Chaos; Cognition; Electronic mail; Gray-scale; Helium; Neural networks; Olfactory; Rabbits; Spatiotemporal phenomena;
Conference_Titel :
TENCON 99. Proceedings of the IEEE Region 10 Conference
Conference_Location :
Cheju Island
Print_ISBN :
0-7803-5739-6
DOI :
10.1109/TENCON.1999.818686
