Title :
Current-mode chaotic neuron with PWL output function for travelling salesman problem
Author :
Kanou, Nobuo ; Horio, Yoshihiko ; Nakamura, Shogo
Author_Institution :
Dept. of Electron. Eng., Tokyo Denki Univ., Japan
Abstract :
This paper investigates the performance of current-mode chaotic neural networks that are optimized for travelling salesman problem (TSP). Piece-wise linear (PWL) functions used as the output functions in chaotic neurons are found to ease the design of neural network circuits. Three different PWL output functions are compared by solving 10-city TSP. Simulation results showed excellent performance of the chaotic neural networks with PWL output function. The design parameters to implement the PWL output function suitable for TSP chaotic neural networks are obtained
Keywords :
CMOS analogue integrated circuits; analogue processing circuits; chaos; neural chips; piecewise-linear techniques; travelling salesman problems; 10-city TSP; PWL output function; current-mode chaotic neuron; design parameters; neural networks; piecewise linear functions; travelling salesman problem; Chaos; Circuit simulation; Clocks; Damping; Neural networks; Neurons; Piecewise linear techniques; Switching circuits; Traveling salesman problems; Very large scale integration;
Conference_Titel :
Circuits and Systems, 1994., Proceedings of the 37th Midwest Symposium on
Conference_Location :
Lafayette, LA
Print_ISBN :
0-7803-2428-5
DOI :
10.1109/MWSCAS.1994.519290
