DocumentCode :
329798
Title :
Dynamical learning of neural networks based on chaotic dynamics
Author :
Kojima, K. ; Ito, K.
Author_Institution :
Dept. of Comput. Intelligence & Syst. Sci., Tokyo Inst. of Technol., Japan
Volume :
4
fYear :
1998
fDate :
11-14 Oct 1998
Firstpage :
3674
Abstract :
This paper proposes a new dynamical memory system based on chaotic neural networks, and its learning scheme. It is demonstrated that, when no embedded pattern, i.e., unknown pattern, is applied to the system, the output pattern travels around the embedded patterns, and the traveling phases depend on a external parameter of the networks such as the input from the other neurons or cortex. Further, the temporal output of the networks reflects a hierarchical structure of the memorized patterns
Keywords :
chaos; content-addressable storage; learning (artificial intelligence); neural nets; chaotic dynamics; cortex; dynamical learning; dynamical memory system; embedded patterns; external parameter; hierarchical structure; memorized patterns; neural networks; output pattern; temporal output; traveling phases; Associative memory; Biological neural networks; Brain modeling; Chaos; Computational intelligence; Neural networks; Neurons; Nonlinear equations; Olfactory; Stability;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Systems, Man, and Cybernetics, 1998. 1998 IEEE International Conference on
Conference_Location :
San Diego, CA
ISSN :
1062-922X
Print_ISBN :
0-7803-4778-1
Type :
conf
DOI :
10.1109/ICSMC.1998.726641
Filename :
726641
Link To Document :
بازگشت