J. C. Sprott, University of Wisconsin - Madison

Abstract: This paper demonstrates that an artificial neural network training on time-series data from the logistic map at the onset of chaos trains more effectively when it is weakly chaotic. This suggests that a modest amount of chaos in the brain in addition to the ever present random noise might be beneficial for learning. In such a case, human subjects might exhibit an increased Lyapunov exponent in their EEG recordings during the performance of creative tasks, suggesting a possible line of future research.

Keywords: chaos, neural networks, training, learning, logistic map