A synthesis method to guarantee symmetric weight matrices for a class of neural networks (which includes the Hopfield neural network as a special case) is proposed. This fills in a gap in the Li-Michel-Porod's synthesis and guarantees asymptotic stability for a given set of linearly independent equilibrium points under Lyapunov's stability criteria.
Published in:
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
(Volume:5
)
Date of Conference: 25-28 May 2003