Open AccessCOMPUTING OF LYAPUNOV EXPONENTS TECHNIQUES USING NEURAL NETWORKS
Author(s) -
Vladimir Golovko,
Yury Savitsky
Publication year - 2014
Publication title -
computing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.184
H-Index - 11
eISSN - 2312-5381
pISSN - 1727-6209
DOI - 10.47839/ijc.3.1.258
Subject(s) - lyapunov exponent , artificial neural network , dynamical systems theory , scalar (mathematics) , lyapunov function , computer science , multilayer perceptron , dynamical system (definition) , perceptron , mathematics , statistical physics , control theory (sociology) , artificial intelligence , chaotic , nonlinear system , physics , control (management) , geometry , quantum mechanics
The authors examine neural network techniques for computing of Lyapunov spectrum using observations from unknown dynamical system. Such an approach is based on applying of multilayer perceptron (MLP) for forecasting the next state of dynamical system from the previous one. It allows for evaluating the Lyapunov spectrum of unknown dynamical system accurately and efficiently only by using scalar time series. The results of experiments are discussed.