Title :
Optical neural network based on the parametrical four-wave mixing process
Author :
Kryzhanovsky, B. ; Litinskii, L.B. ; Fonarev, A.
Author_Institution :
Inst. of Opt. Neural Technol., Acad. of Sci., Moscow, Russia
Abstract :
In this paper we develop a formalism allowing us to describe operating of a network based on the parametrical four-wave mixing process that is well-known in nonlinear optics. The recognition power of a network using parametric neurons operating with q different frequencies is considered. It is shown that the storage capacity of such a network is higher compared with the Potts-glass models.
Keywords :
multiwave mixing; optical neural nets; optical storage; network recognition power; network storage capacity; nonlinear optics; optical neural network; parametric neurons; parametrical four-wave mixing process; Four-wave mixing; Frequency; Neural networks; Neurons; Nonlinear optics; Optical computing; Optical fiber networks; Optical filters; Optical mixing; Signal processing;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1198966
