Title :
Recurrent neural networks: overview and perspectives
Author :
Michel, Anthony N.
Author_Institution :
Dept. of Electr. Eng., Notre Dame Univ., IN, USA
Abstract :
In the implementation of artificial neural networks, several limitations are encountered which may affect their qualitative behavior and performance. These include delays, parameter perturbations and interconnection constraints. Depending on the particular type of implementation, more than one of these limitations will usually be encountered simultaneously. In the present paper, we address these issues.
Keywords :
asymptotic stability; delays; interconnections; recurrent neural nets; robust control; sparse matrices; asymptotically stable equilibrium; interconnection constraints; overview; parameter perturbations; qualitative behavior; recurrent neural networks; robust stability; sparse coefficient matrices; time delays; Artificial neural networks; Delay effects; Equations; Intelligent networks; Neural networks; Neurons; Recurrent neural networks; Symmetric matrices; Transportation; Very large scale integration;
Conference_Titel :
Circuits and Systems, 2003. ISCAS '03. Proceedings of the 2003 International Symposium on
Print_ISBN :
0-7803-7761-3
DOI :
10.1109/ISCAS.2003.1205059
