Title :
An artificial network based on unfixed states number oscillators
Author :
Golovin, Oleg L.
Author_Institution :
Kurchatov Inst. of Atomic Energy, Moscow, USSR
Abstract :
The properties of neural networks based on different oscillators with an unfixed number of states and intended for optical and hybrid implementation are investigated. The pattern recognition time depends on the computation accuracy and floating threshold, and may be less than the oscillation period. A model of the network has been developed which makes it possible to investigate some network features for different parameters and functions, and to describe the oscillator interaction methods, the learning rules, the pattern correlation indicators, and the synchronization level indexes
Keywords :
learning systems; neural nets; optical information processing; oscillators; pattern recognition; synchronisation; computation accuracy; floating threshold; learning rules; model; neural networks; oscillator interaction; pattern correlation indicators; pattern recognition time; synchronization level indexes; Angular velocity; Hardware; Hebbian theory; Liquid crystal on silicon; Oscillators; Pattern recognition; Surges;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170366
