<abstract xml:lang="en" xmlns="http://www.w3.org/1999/xhtml"><p>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.</p></abstract>

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.

Local stability conditions for discrete-time cascade locally recurrent neural networks

Institute of Control and Computation Engineering, University of Zielona Góra, ul. Podgórna 50, 65-246 Zielona Góra, Poland

International Journal of Applied Mathematics and Computer Science

The paper deals with a specific kind of discrete-time recurrent neural network designed with dynamic neuron models. Dynamics are reproduced within each single...

Local stability conditions for discrete-time cascade locally recurrent neural networks

Published Online: Mar 25, 2010

Page range: 23 - 34

DOI: https://doi.org/10.2478/v10006-010-0002-x

Keywords
locally recurrent neural network, stability, stabilization, learning, constrained optimization

This content is open access.

Local stability conditions for discrete-time cascade locally recurrent neural networks

Published Online: Mar 25, 2010

Page range: 23 - 34

DOI: https://doi.org/10.2478/v10006-010-0002-x

Keywordslocally recurrent neural network, stability, stabilization, learning, constrained optimization

This content is open access.

Keywords
locally recurrent neural network, stability, stabilization, learning, constrained optimization