Title :
A neural network using oscillators
Author :
Endo, Tetsuro ; Chua, L.O. ; Takeyama, Kazuhiro
Author_Institution :
Dept. of Electr. Eng., Nat. Defense Acad., Yokosuka, Japan
Abstract :
The authors propose the oscillator neural network, in which the sigmoid nonlinearity of the Hopfield neural network is replaced by the Van der Pol oscillator. The oscillator neural network has the advantage that no simulated annealing is necessary to obtain a reasonable solution. They demonstrate that the 4-b analog to digital (A/D) converter problem, the 10-city traveling salesman problem and the associative memory problem, can be solved by the proposed neural network
Keywords :
analogue-digital conversion; content-addressable storage; neural nets; nonlinear network synthesis; relaxation oscillators; 10-city traveling salesman problem; 4 bit; A/D converter; Hopfield neural network; Van der Pol oscillator; associative memory problem; oscillator neural network; Associative memory; Circuit simulation; Electronic circuits; High level synthesis; Hopfield neural networks; Large-scale systems; Neural networks; Oscillators; Simulated annealing; Traveling salesman problems;
Conference_Titel :
Circuits and Systems, 1991., IEEE International Sympoisum on
Print_ISBN :
0-7803-0050-5
DOI :
10.1109/ISCAS.1991.176479
