Title :
A chaos memory model
Author :
Nakagawa, Masahiro
Author_Institution :
Fac. of Eng., Nagaoka Univ. of Technol., Niigata, Japan
Abstract :
In this paper we explore that a chaos neural network (CNN) model with a sinusoidal activation function may realise ~10-20 times larger memory capacity than CNN with conventionally proposed sigmoidal activation function proposed by K. Aihara et al (1990). In fact the complete association is found to be promoted up to ~100% loading rate even though a relevant noise is involved in an input vector
Keywords :
chaos; neural nets; chaos memory model; chaos neural network model; sigmoidal activation function; sinusoidal activation function; Associative memory; Autocorrelation; Cellular neural networks; Chaos; Computer aided manufacturing; Joining processes; Neural networks; Neurons; Optimal control; Traveling salesman problems;
Conference_Titel :
Systems, Man, and Cybernetics, 1999. IEEE SMC '99 Conference Proceedings. 1999 IEEE International Conference on
Conference_Location :
Tokyo
Print_ISBN :
0-7803-5731-0
DOI :
10.1109/ICSMC.1999.814126
