Volume 123, Number 5, September 2018
|Number of page(s)||7|
|Section||Interdisciplinary Physics and Related Areas of Science and Technology|
|Published online||27 September 2018|
Self-organizing dynamical networks able to learn autonomously
Interdisciplinary Institute of Basic Sciences, National Scientific and Technical Research Council (CONICET) & Faculty of Exact and Natural Sciences, National University of Cuyo - Padre Contreras 1300, 5500 Mendoza, Argentina
Received: 4 July 2018
Accepted: 3 September 2018
We present a model for the time evolution of network architectures based on dynamical systems. We show that the evolution of the existence of a connection in a network can be described as a stochastic non-Markovian telegraphic signal (NMTS). Such signal is formulated in two ways: as an algorithm and as the result of a system of differential equations. The autonomous learning conjecture (Kaluza P. and Mikhailov A. S., Phys. Rev. E, 90 (2014) 030901(R)) is implemented in the proposed dynamics. As a result, we construct self-organizing dynamical systems (networks) able to modify their structures in order to learn prescribed target functionalities. This theory is applied to two systems: the flow processing networks with time-programmed responses, and a system of first-order chemical reactions. In both cases, we show examples of the evolution and a statistical analysis of the obtained functional networks with respect to the model parameters.
PACS: 89.75.Hc – Networks and genealogical trees / 05.65.+b – Self-organized systems / 05.45.-a – Nonlinear dynamics and chaos
© EPLA, 2018
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.