DocumentCode
314378
Title
Global stability analysis of a nonlinear principal component analysis neural network
Author
Meyer-Bäse, Anke
Author_Institution
Dept. of Comput. & Electr. Eng., Florida Univ., Gainesville, FL, USA
Volume
3
fYear
1997
fDate
9-12 Jun 1997
Firstpage
1785
Abstract
The self-organization of a nonlinear, single-layer neural network is mathematically analyzed, in which a regular Hebbian rule and an anti-Hebbian rule are used for the adaptation of the connection weights between the constituent units. It is shown that the equilibrium points of this system are global asymptotically stable. Following some restrictive assumptions a nonlinear principal component analyzer can be constructed
Keywords
Hebbian learning; asymptotic stability; nonlinear systems; self-organising feature maps; anti-Hebbian rule; global asymptotic stability; global stability analysis; nonlinear principal component analysis neural network; nonlinear principal component analyzer; nonlinear single-layer neural network; regular Hebbian rule; Asymptotic stability; Computer networks; Laboratories; Neural engineering; Neural networks; Neurons; Nonlinear dynamical systems; Nonlinear equations; Principal component analysis; Stability analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks,1997., International Conference on
Conference_Location
Houston, TX
Print_ISBN
0-7803-4122-8
Type
conf
DOI
10.1109/ICNN.1997.614167
Filename
614167
Link To Document