Local input-output stability of recurrent networks with time-varying weights

Abstract. We present local conditions for input-output stability of recurrent neural networks with time-varying parameters introduced for instance by noise or on-line adaptation. The conditions guarantee that a network implements a proper mapping from time-varying input to time-varying output functions using a local equilibrium as point of operation. We show how to calculate necessary bounds on the allowed inputs to keep the network in the stable range and apply the method to an example of learning an input-output map implied by the chaotic Roessler attractor.

• Type: Conference
• Year: 2000
• Where: ESANN
• Authors: Jochen J. Steil
• Keywords: ESANN 2000, ESANN 2007, Time-varying Input, Time-varying Output Functions, Time-varying Parameters