Advanced Search

Query:

Fill in the form and click »Search«...

Format:

Display: entries per page entries

Zbl 0887.34069
Olien, Leonard; Bélair, Jacques
Bifurcations, stability, and monotonicity properties of a delayed neural network model. (English)
[J] Physica D 102, No.3-4, 349-363 (1997). ISSN 0167-2789

Summary: A delay-differential equation modelling an artificial neural network with two neurons is investigated. A linear stability analysis provides parameter values yielding asymptotic stability of the stationary solutions: these can lose stability through either a pitchfork or a Hopf bifurcation, which is shown to be supercritical. At appropriate parameter values, an interaction takes place between the pitchfork and Hopf bifurcations. Conditions are also given for the set of initial conditions that converge to a stable stationary solution to be open and dense in the functional phase space. Analytic results are illustrated with numerical simulations.

MSC 2000:: *34K20 Stability theory of functional-differential equations
92B20 General theory of neural networks

Keywords: delay-differential equation; artificial neural network; asymptotic stability; stationary solutions; Hopf bifurcation

Comment on this Item PDF MathML XML ASCII DVI PS BibTeX Online Ordering Article Journal

	Scientific prize winners of the ICM 2010
	Overhang
	Lie groups, physics and geometry. An introduction for physicists, engineers and chemists.

Advanced Search

Zentralblatt MATH Berlin [Germany]