Title :
Holographic implementation of a fully connected neural network
Author :
Hsu, Ken-Yuh ; Li, Hsin-Yu ; Psaltis, Demetri
Author_Institution :
Dept. of Electr. Eng., California Inst. of Technol., Pasadena, CA, USA
fDate :
10/1/1990 12:00:00 AM
Abstract :
A holographic implementation of a fully connected neural network is presented. This model has a simple structure and is relatively easy to implement, and its operating principles and characteristics can be extended to other types of networks, since any architecture can be considered as a fully connected network with some of its connections missing. The basic principles of the fully connected network are reviewed. The optical implementation of the network is presented. Experimental results which demonstrate its ability to recognize stored images are given, and its performance and analysis are discussed based on a proposed model for the system. Special attention is focused on the dynamics of the feedback loop and the tradeoff between distortion tolerance and image-recognition capability of the associative memory
Keywords :
computerised pattern recognition; content-addressable storage; holographic storage; neural nets; optical information processing; associative memory; distortion tolerance; feedback loop; holography; image-recognition; neural network; optical computing; pattern recognition; Feedback loop; Holographic optical components; Holography; Image analysis; Image recognition; Neural networks; Optical distortion; Optical feedback; Optical fiber networks; Performance analysis;
Journal_Title :
Proceedings of the IEEE
