Stability Analysis and the Stabilization of a Class of Discrete-Time Dynamic Neural Networks
Patan, K.
Inst. of Control & Comput. Eng., Univ. of Zielona Gora, Zielona Goraversity;
This paper appears in: Neural Networks, IEEE Transactions on
Publication Date: May 2007
Volume: 18,
Issue: 3
On page(s): 660-673
ISSN: 1045-9227
INSPEC Accession Number: 9437828
Digital Object Identifier: 10.1109/TNN.2007.891199
Current Version Published: 2007-05-07
Abstract
This paper deals with problems of stability and the stabilization of discrete-time neural networks. Neural structures under consideration belong to the class of the so-called locally recurrent globally feedforward networks. The single processing unit possesses dynamic behavior. It is realized by introducing into the neuron structure a linear dynamic system in the form of an infinite impulse response filter. In this way, a dynamic neural network is obtained. It is well known that the crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates stability conditions for the analyzed class of neural networks. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem two methods are proposed. The first one is based on a gradient projection (GP) and the second one on a minimum distance projection (MDP). It is worth noting that these methods can be easily introduced into the existing learning algorithm as an additional step, and suitable convergence conditions can be developed for them. The efficiency and usefulness of the proposed approaches are justified by using a number of experiments including numerical complexity analysis, stabilization effectiveness, and the identification of an industrial process
Index
Terms
Available to subscribers and IEEE members.
References
Available to subscribers and IEEE members.
Citing Documents
Available to subscribers and IEEE members.
Cart
