Stability of stochastic delay neural networks (Q5939354)

The stochastically perturbed network with delays \[ dx(t)= \bigl[ -Bx(t)+ Ag\bigl(x_\tau (t)\bigr) \biggr]dt +\sigma\bigl( x(t),x_\tau (t), t\bigr)dw(t), t\geq 0;\;x(s)=\xi(s),\;-\tau\leq s\leq 0;\tag{1} \] is considered. Here \(w(t)\) is an \(m\)-dimensional Brownian motion, \(\sigma(x,y,t)\) is locally Lipschitz continuous and satisfies the linear growth conditions. Several sufficient criteria are established for almost sure exponential stability of (1).