Radiotekhnika
Publishing house Radiotekhnika

"Publishing house Radiotekhnika":
scientific and technical literature.
Books and journals of publishing houses: IPRZHR, RS-PRESS, SCIENCE-PRESS


Тел.: +7 (495) 625-9241

 

The possibility of using some of the characteristics of self-synchronization to identify clusters in the oscillator neural network with chaotic dynamics

Keywords:

E.N. Benderskaya


Chaotic dynamics of oscillatory nonlinear mapping neural networks are discussed. Oscillatory neural network dynamics has specific capabilities for self-organization in the form of oscillatory clusters emergence. Oscillatory clusters correspond groups of neurons that change their states synchronously via time. This phenomenon can be applied to solve data clustering problems after we find the proper way to translate synchronous clusters into data clusters. Various synchronization measures are observed. In order to understand the chaotic synchronization phenomenon the mutual metrics of neurons pairs in the multidimensional space of outputs should be considered.
References:

© Издательство «РАДИОТЕХНИКА», 2004-2017            Тел.: (495) 625-9241                   Designed by [SWAP]Studio