DocumentCode
300771
Title
Global stability for a class of dynamical neural networks
Author
Fang, Yuguang ; Kincaid, Thomas G.
Author_Institution
Dept. of Electr. Comput. & Syst. Eng., Boston Univ., MA, USA
Volume
4
fYear
1995
fDate
21-23 Jun 1995
Firstpage
2762
Abstract
Studies the global properties of a class of asymmetrical Hopfield-type neural circuits. The authors first present a result for the existence and uniqueness of an equilibrium point; this result does not assume smoothness of the neural activation functions. Then the authors give some testable sufficient conditions for the global stability of such neural circuits. These results generalize a few previous known results and remove some restrictions on the neural circuits
Keywords
Hopfield neural nets; matrix algebra; stability; transfer functions; asymmetrical Hopfield-type neural circuits; dynamical neural networks; equilibrium point; existence; global stability; testable sufficient conditions; uniqueness; Circuit stability; Circuit testing; Eigenvalues and eigenfunctions; Integrated circuit interconnections; Linear matrix inequalities; Neural networks; Robust stability; Sufficient conditions; Symmetric matrices; Systems engineering and theory;
fLanguage
English
Publisher
ieee
Conference_Titel
American Control Conference, Proceedings of the 1995
Conference_Location
Seattle, WA
Print_ISBN
0-7803-2445-5
Type
conf
DOI
10.1109/ACC.1995.532352
Filename
532352
Link To Document