Hetero associative neural network for pattern recognition

Author

Lu, Taiwei ; Xu, Xin ; Wu, Shudong ; Yu, Francis T S

Author_Institution

Dept. of Electr. Eng., Pennsylvania State Univ., University Park, PA, USA

fYear

1989

fDate

14-17 Nov 1989

Firstpage

658

Abstract

An inter-pattern association (IPA) neural network model is presented in which basic logical operations are used to determine the association among common and special features of reference patterns. Hetero- and auto-associative memory are synthesized by applying a generalized logical rule. Computer simulations for pattern recognition by using the IPA model have shown a better performance and a higher storage capacity than the Hopfield model. A 2-D adaptive optical neural network is used to perform parallel neurocomputations. Since the interconnection weight matrix for the IPA model has a tristate structure, the dynamic range imposed on a spatial light modulator is rather relaxed, and the interconnections are much simpler than for the Hopfield model

Keywords

content-addressable storage; neural nets; pattern recognition; 2-D adaptive optical neural network; hetero associative neural network; parallel neurocomputations; pattern recognition; reference patterns; storage capacity; Adaptive optics; Adaptive systems; Computer simulation; Network synthesis; Neural networks; Optical computing; Optical fiber networks; Optical interconnections; Optical modulation; Pattern recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man and Cybernetics, 1989. Conference Proceedings., IEEE International Conference on

Conference_Location

Cambridge, MA

Type

conf

DOI

10.1109/ICSMC.1989.71378

Filename

71378