Reference:
Jiří Šíma and Pekka Orponen. Exponential transients in continuoustime Liapunov systems. Theoretical Computer Science, 306(1–3):353–372, September 2003.
Abstract:
We consider the convergence behavior of a class of continuoustime dynamical systems corresponding to so called symmetric Hopfield nets studied in neural networks theory. We prove that such systems may have transient times that are exponential in the system dimension (i.e. number of "neurons"), despite the fact that their dynamics are controlled by Liapunov functions. This result stands in contrast to many proposed uses of such systems in e.g. combinatorial optimization applications, in which it is often implicitly assumed that their convergence is rapid. An additional interesting observation is that our example of an exponentialtransient continuoustime system (a simulated binary counter) in fact converges more slowly than any discretetime Hopfield system of the same representation size. This suggests that continuoustime systems may be worth investigating for gains in descriptional efficiency as compared to their discretetime counterparts.
Keywords:
dynamical systems, continuous time, convergence rate, neural networks, Hopfield model
Suggested BibTeX entry:
@article{SiOr03b,
author = {Ji{\v{r}}{\'{\i}} {\v{S}}{\'{\i}}ma and Pekka Orponen},
journal = {Theoretical Computer Science},
month = {September},
number = {13},
pages = {353372},
title = {Exponential Transients in ContinuousTime {L}iapunov Systems},
volume = {306},
year = {2003},
}
