Title :
Associative memory by Hopfield NN with chaos injection
Author :
Uwate, Yoko ; Nishio, Yoshifumi ; Ikeguchi, Tohru
Author_Institution :
Tokushima Univ., Japan
Abstract :
Several people point out that the Hopfield neural network (abbr.NN ) with chaos injection gains the good performance for solving traveling salesman problems, which is one of combinatorial optimization problems. In this study, we investigate the performance of the intermittency chaos injected to the Hopfield NN working as an associative memory. The rate and the speed of the convergence to an embedded pattern are evaluated by computer simulations.. Furthermore, in order to confirm the reason of the good ability of intermittency chaos, we carry out the same simulation using the time series produced by the Markov chain model. Simulated results show that the Markov chain model is good enough to gain similar performance of the intermittency chaos.
Keywords :
Hopfield neural nets; Markov processes; chaos; content-addressable storage; time series; travelling salesman problems; Hopfield neural network; Markov chain model; associative memory; chaos injection; combinatorial optimization problems; time series; traveling salesman problems; Associative memory; Chaos; Computational modeling; Computer simulation; Convergence; Electronic mail; Neural networks; Neurons; Performance gain; Traveling salesman problems;
Conference_Titel :
Neural Networks, 2004. Proceedings. 2004 IEEE International Joint Conference on
Print_ISBN :
0-7803-8359-1
DOI :
10.1109/IJCNN.2004.1379873
