A Phasor Model with Resting States

Teruyuki MIYAJIMA  Fumihito BAISHO  Kazuo YAMANAKA  Kazuhiko NAKAMURA  Masahiro AGU  

IEICE TRANSACTIONS on Information and Systems   Vol.E83-D   No.2   pp.299-301
Publication Date: 2000/02/25
Online ISSN: 
Print ISSN: 0916-8532
Type of Manuscript: LETTER
Category: Biocybernetics, Neurocomputing
neural networks,  associative memory,  complex-valued neuron,  stability analysis,  Lyapunov theory,  

Full Text: PDF>>
Buy this Article

A new phasor model of neural networks is proposed in which the state of each neuron possibly takes the value at the origin as well as on the unit circle. A stability property of equilibria is studied in association with the energy landscape. It is shown that a simple condition guarantees an equilibrium to be asymptotically stable.