Crossing the quasi-threshold manifold of a noise-driven excitable system.

We consider the noise-induced escapes in an excitable system possessing a quasi-threshold manifold, along which there exists a certain point of minimal quasi-potential. In the weak noise limit, the optimal escaping path turns out to approach this particular point asymptotically, making it analogous to an ordinary saddle. Numerical simulations are performed and an elaboration on the effect of small but finite noise is given, which shows that the ridges where the prehistory probability distribution peaks are located mainly within the region where the quasi-potential increases gently. The cases allowing anisotropic noise are discussed and we found that varying the noise term in the slow variable would dramatically raise the whole level of quasi-potentials, leading to significant changes in both patterns of optimal paths and exit locations.