Stability constraints for oscillatory neural networks

The stability of the equilibrium point (background activity) of oscillatory neural networks is an important property for computational applications that explore the switching between background activity and oscillatory states. Here we consider a general approach to this problem for networks of arbitrary size. For symmetric coupling, often the case in associative learning algorithms, we derive the stability constraints and establish explicit results for the coupling strengths to satisfy in order that the equilibrium state is stable. ( 2000 Elsevier Science B.V. All rights reserved.