Phase space structure of neural networks for pattern recognition

Eugene I. Shubnikov

doi:10.1117/12.166066

21 January 1994 Phase space structure of neural networks for pattern recognition

Eugene I. Shubnikov

Proceedings Volume 2051, International Conference on Optical Information Processing; (1994) https://doi.org/10.1117/12.166066
Event: Optical Information Processing: International Conference, 1993, St. Petersburg, Russian Federation

Abstract

The investigation of phase space structure of neural networks based on image correlation for pattern recognition is presented. The network has analog input and attractors as stationary points. Correlation of patterns is taken into consideration. Input images are spatially separated and they are represented as a stochastic field. Correlation theory is used to receive the analytical expressions. The maximum depth and width of a true attractor, the depth of false attractors, and the depth of a true attractor in comparison with false ones are received.

Citation Download Citation

Eugene I. Shubnikov "Phase space structure of neural networks for pattern recognition", Proc. SPIE 2051, International Conference on Optical Information Processing, (21 January 1994); https://doi.org/10.1117/12.166066

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