Share Email Print

Proceedings Paper

Las Vegas method of region-of-attraction enlargement in neural networks
Author(s): Y. Smetanin
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 19 January 1995
PDF: 5 pages
Proc. SPIE 2363, 5th International Workshop on Digital Image Processing and Computer Graphics (DIP-94), (19 January 1995); doi: 10.1117/12.199655
Show Author Affiliations
Y. Smetanin, Scientific Council Cybernetics (Russia)

Published in SPIE Proceedings Vol. 2363:
5th International Workshop on Digital Image Processing and Computer Graphics (DIP-94)
Nikolai A. Kuznetsov; Victor A. Soifer, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?