Las Vegas method of region-of-attraction enlargement in neural networks

Y. Smetanin

doi:10.1117/12.199655

19 January 1995 Las Vegas method of region-of-attraction enlargement in neural networks

Y. Smetanin

Proceedings Volume 2363, 5th International Workshop on Digital Image Processing and Computer Graphics (DIP-94); (1995) https://doi.org/10.1117/12.199655
Event: Digital Image Processing and Computer Graphics: Fifth International Workshop, 1994, Samara, Russian Federation

Abstract

The problem of the design of unerring neural networks with block structure is considered. The bottleneck is building faultless blocks without spurious states. All the commonly used rules of recurrent neural network learning don't exclude the possibility of spurious state apparition in the stable state neighborhoods. In recognition problems these spurious states cause false solutions deteriorating over the network and destroying its robustness. The problem of finding the number and localizing the stable states in neural networks with polynomial capacity without oscillations is considered. A method is proposed to detect spurious states that are close to the stable states of a given network. The method is based on random sampling. It is fast and almost always finds dangerous spurious states. The algorithm is of Las Vegas type and can find the centers and approximate sizes of all the basins of attraction that are great enough. The evaluation of the test time and the probability of the test correctness are given. The number of operations is polynomial unless the capacity is exponential. Some approaches to spurious state suppression are proposed. The results of experiments with some neural network models are briefly described.

Citation Download Citation

Y. Smetanin "Las Vegas method of region-of-attraction enlargement in neural networks", Proc. SPIE 2363, 5th International Workshop on Digital Image Processing and Computer Graphics (DIP-94), (19 January 1995); https://doi.org/10.1117/12.199655

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