Operator formalism for optical neural network based on the parametrical four-wave mixing process

2012/08/08 by Leonid Litinskii, L. B. Litinskii, Boris Kryzhanovsky +5
Computer Science · Engineering · Physics and Astronomy · #60 #94 #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #Photonic and Optical Devices #cond-mat.dis-nn #cs.ET #msc:60 #msc:94

paper · pdf · doi:10.48550/arxiv.1208.1774

5 pages,without figures

arxiv created 2012/08/08 · openalex publication_date 2012/08/08 · arxiv updated 2012/08/10 · openalex created_date 2016/06/24 · openalex updated_date 2026/07/28

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.

Related

• Parametrical Neural Network
• Parametrical Neural Networks and Some Other Similar Architectures
• Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation
• Universality of physical neural networks with multivariate nonlinearity
• Solving classification tasks by a receptron based on nonlinear optical speckle fields