Development of the new Neuroglial approach: Application on singularly perturbed systems

In this paper, we propose a new modular architecture that emulates a biological reality recently discovered. The implementation is based on complex multi-time scale systems; validation is performed on the model of the asynchronous machine putting in the standard singularly perturbed form. We applied the geometrical approach based on the Gerschgorin circles to separate the fast and slow variables, as well as the singular perturbation method for determining the reduced models. This new architecture allows for smaller networks with less complexity and better performance in terms of MSE error and convergence speed than the single network model.