NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Optical-Correlator Neural Network Based On NeocognitronMultichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.
Document ID
19940000300
Acquisition Source
Legacy CDMS
Document Type
Other - NASA Tech Brief
Authors
Chao, Tien-Hsin
(Caltech)
Stoner, William W.
(Science Applications International Corp.)
Date Acquired
August 16, 2013
Publication Date
May 1, 1994
Publication Information
Publication: Laser Tech. Brief.
Volume: 2
Issue: 2
Subject Category
Electronic Systems
Report/Patent Number
NPO-18988
Accession Number
94B10300
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Available Downloads

There are no available downloads for this record.
No Preview Available