Premium
Neuronal state feedback learning of Cohen–Grossberg networks
Author(s) -
Apostolou N.,
King R. E.
Publication year - 1999
Publication title -
international journal of circuit theory and applications
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.364
H-Index - 52
eISSN - 1097-007X
pISSN - 0098-9886
DOI - 10.1002/(sici)1097-007x(199905/06)27:3<331::aid-cta50>3.0.co;2-8
Subject(s) - attractor , equilibrium point , artificial neural network , exponential stability , class (philosophy) , associative property , stability (learning theory) , computer science , affine transformation , state (computer science) , control theory (sociology) , connectionism , point (geometry) , differential equation , mathematics , control (management) , artificial intelligence , algorithm , nonlinear system , machine learning , pure mathematics , mathematical analysis , physics , geometry , quantum mechanics
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.