Vector neural net identifying many strongly distorted and correlated patterns

Boris V. Kryzhanovsky; Andrei L. Mikaelian; Anatoly B. Fonarev

doi:10.1117/12.572334

11 January 2005 Vector neural net identifying many strongly distorted and correlated patterns

Boris V. Kryzhanovsky, Andrei L. Mikaelian, Anatoly B. Fonarev

Proceedings Volume 5642, Information Optics and Photonics Technology; (2005) https://doi.org/10.1117/12.572334
Event: Photonics Asia, 2004, Beijing, China

Abstract

We suggest an effective and simple algorithm providing a polynomial storage capacity of a network of the form M ~ N^2s+1, where N is the dimension of the stored binary patterns. In this problem the value of the free parameter s is restricted by the inequalities N >> slnN ≥ 1. The algorithm allows us to identify a large number of highly distorted similar patterns. The negative influence of correlations of the patterns is suppressed by choosing a sufficiently large value of the parameter s. We show the efficiency of the algorithm by the example of a perceptron identifier, but it also can be used to increase the storage capacity of full connected systems of associative memory.

Citation Download Citation

Boris V. Kryzhanovsky, Andrei L. Mikaelian, and Anatoly B. Fonarev "Vector neural net identifying many strongly distorted and correlated patterns", Proc. SPIE 5642, Information Optics and Photonics Technology, (11 January 2005); https://doi.org/10.1117/12.572334

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