Premium
Optical implementation of A 2‐D neural net with a third‐order interconnection for image quadratic associative memory based on a compact‐encoding method
Author(s) -
Lin Senmao,
Wu Jie,
Liu Liren
Publication year - 1989
Publication title -
microwave and optical technology letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.304
H-Index - 76
eISSN - 1098-2760
pISSN - 0895-2477
DOI - 10.1002/mop.4650020809
Subject(s) - interconnection , encoding (memory) , content addressable memory , computer science , associative property , image (mathematics) , quadratic equation , artificial neural network , net (polyhedron) , implementation , parallel computing , algorithm , mathematics , artificial intelligence , telecommunications , geometry , pure mathematics , programming language
The optical implementations of a 2‐D neural net with a third‐order interconnection for image quadratic associative memory are reported. Two types of incoherent optical systems, based on multiple imaging and correlation, are used. In particular, a compact‐encoding method, which can greatly reduce the size of the interconnection tensor, is also proposed. The experimental results are given.