Optical implementation of a shift-invariant neocognitron

Tien-Hsin Chao; William W. Stoner; William J. Miceli

doi:10.1117/12.983186

2 February 1993 Optical implementation of a shift-invariant neocognitron

Tien-Hsin Chao, William W. Stoner, William J. Miceli

Proceedings Volume 1773, Photonics for Computers, Neural Networks, and Memories; (1993) https://doi.org/10.1117/12.983186
Event: San Diego '92, 1992, San Diego, CA, United States

Abstract

An optical neural network based upon the Neocognitron paradigm is introduced. A novel aspect of the architectural design is shift-invariant multichannel Fourier optical correlation within each processing layer. An innovative bipolar neural weights holographic synthesis technique is introduced to implement both the excitatory and inhibitory neural functions. Multilayer processing is achieved by iteratively feeding back the output of the feature correlator to the input spatial light modulator and updating the Fourier filters. By designing the neural net with characteristic features extracted from the target images, successful pattern recognition with intra-class fault tolerance and inter-class discrimination is achieved. A detailed system description is provided. Experimental demonstrations of a two-layer neural network for space objects discrimination is also presented.

Citation Download Citation

Tien-Hsin Chao, William W. Stoner, and William J. Miceli "Optical implementation of a shift-invariant neocognitron", Proc. SPIE 1773, Photonics for Computers, Neural Networks, and Memories, (2 February 1993); https://doi.org/10.1117/12.983186

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available