Korbicz, Józef - red. ; Uciński, Dariusz - red.
The paper deals with a specific kind of discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single neuron, hence the network considered is a locally recurrent globally feedforward. A crucial problem with neural networks of the dynamic type is stability as well as stabilization in learning problems. The paper formulates local stability conditions for the analysed class of neural networks using Lyapunov?s first method. Moreover, a stabilization problem is defined and solved as a constrained optimization task. In order to tackle this problem, a gradient projection method is adopted. The efficiency and usefulness of the proposed approach are justified by using a number of experiments.
Zielona Góra: Uniwersytet Zielonogórski
AMCS, Volume 20, Number 1 (2010) ; click here to follow the link
Biblioteka Uniwersytetu Zielonogórskiego
Sep 7, 2021
Aug 10, 2018
|Local stability conditions for discrete-time cascade locally recurrent neural networks||Sep 7, 2021|
Songschon, Szathys Longman, Richard W. Korbicz, Józef - red. Uciński, Dariusz - red.
Korbicz, Józef Patan, Krzysztof Obuchowicz, Andrzej Korbicz, Józef - red. Patton, Ronald J. - red.
Stavroulaki, Maria E. Stavroulakis, Georgios E. Sofonea, Mircea - ed. Viano, Juan M. - ed.
Correia, Aldina Matias, Joáo Mestre, Pedro Serodio, Carlos Korbicz, Józef - red. Uciński, Dariusz - red.
Zerrik, El Hassan Ouzahra, Mohamed Korbicz, Józef - red. Uciński, Dariusz - red.
Tatjewski, Piotr Korbicz, Józef - red. Uciński, Dariusz - red.
Jankowski, Norbert Korbicz, Józef - red. Uciński, Dariusz - red.
Hammami, Mohamed Ali Jerbi, Hamadi Korbicz, Józef - red. Uciński, Dariusz - red.