G. Deco et B. Schurmann, NEURAL LEARNING OF CHAOTIC SYSTEM BEHAVIOR, IEICE transactions on fundamentals of electronics, communications and computer science, E77A(11), 1994, pp. 1840-1845
Citations number
NO
Categorie Soggetti
Engineering, Eletrical & Electronic","Computer Science Hardware & Architecture","Computer Science Information Systems
We introduce recurrent networks that are able to learn chaotic maps, a
nd investigate whether the neural models also capture the dynamical in
variants (Correlation Dimension, largest Lyapunov exponent) of chaotic
time series. We show that the dynamical invariants can be learned alr
eady by feedforward neural networks, but that recurrent learning impro
ves the dynamical modeling of the time series. We discover a novel typ
e of overtraining which corresponds to the forgetting of the largest L
yapunov exponent during learning and call this phenomenon dynamical ov
ertraining. Furthermore, we introduce a penalty term that involves a d
ynamical invariant of the network and avoids dynamical overtraining. A
s examples we use the Henon map, the logistic map and a real world cha
otic series that corresponds to the concentration of one of the chemic
als as a function of time in experiments on the Belousov-Zhabotinskii
reaction in a well-stirred flow reactor.