A Horseshoe in a Cellular Neural Network of Four-Dimensional Autonomous Ordinary Differential Equations

We obtain numerically a horseshoe in a Poincare map derived from a cellular neural network described by four-dimensional autonomous ordinary differential equations. Contrary to the horseshoe numerically found in the Hodgkin–Huxley model, which showed evidence that the Poincare map derived from the Hodgkin–Huxley model has just one expanding direction on some invariant subset, the horseshoe obtained in this paper proves that the Poincare map derived from the neural network have two expanding directions on some invariant subset.