Neuronal state feedback learning of Cohen-Grossberg networks

• Published in: International journal of circuit theory and applications Vol. 27; no. 3; pp. 331 - 338
• Main Authors: Apostolou, N., King, R. E.
• Format: Journal Article
• Language: English
• Published: Chichester, UK John Wiley & Sons, Ltd 01-05-1999; Wiley
• Subjects: adaptive neural networks; Applied sciences; autoassociative networks; Electric, optical and optoelectronic circuits; Electronics; Exact sciences and technology; Theoretical study. Circuits analysis and design; weight training; Non linear equation; Computer simulation; Differential equation; Stabilization; Neural network; Autoassociative network; Affine transformation; Adaptive neuronal network; Lyapunov function; Circuit theory; State variable
• ISSN: 0098-9886; 1097-007X
• DOI: 10.1002/(SICI)1097-007X(199905/06)27:3<331::AID-CTA50>3.0.CO;2-8

This paper proposes a direct synaptic weight training technique for a class of additive dynamic auto‐associative neural networks based on the Cohen–Grossberg neuronal activation model. The proposed technique is based on the Jurdjevic–Quinn stabilization method for control affine systems. Asymptotic stability of the training law is guaranteed and regions of attraction around each point attractor are predefined. The proposed technique requires the solution of significantly fewer non‐linear differential equations and is considerably simpler and faster than existing training techniques. Copyright © 1999 John Wiley & Sons, Ltd.