Article
Counterexample of a Claim Pertaining to the Synthesis of a Recurrent Neural Network
Proceedings of the 2002 International Joint Conference on Neural Networks, 2002. IJCNN '02
Abstract
Recurrent neural networks have received much attention due to their nonlinear dynamic behavior. One such type of dynamic behavior is that of setting a fixed stable state. This paper shows a counterexample to the claim of A.N. Michel et al. (IEEE Control Systems Magazine, vol. 15, pp. 52-65, Jun. 1995), that "sparse constraints on the interconnecting structure for a given neural network are usually expressed as constraints which require that pre-determined elements of T [a real n×n matrix acting on a real n-vector valued function] be zero", for the synthesis of sparsely interconnected recurrent neural networks.
Meeting Name
2002 International Joint Conference on Neural Networks, 2002. IJCNN '02
Department(s)
Electrical and Computer Engineering
Keywords and Phrases
- Constraint Theory,
- Fixed Stable State,
- Network Synthesis,
- Neural Net Interconnecting Structure,
- Nonlinear Dynamic Behavior,
- Pre-Determined Matrix Elements,
- Recurrent Neural Nets,
- Recurrent Neural Network Synthesis,
- Sparse Constraints,
- Sparse Matrices,
- Sparsely Interconnected Networks,
- Stability
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 2002 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
1-1-2002
Publication Date
01 Jan 2002
Disciplines
Citation Information
Xindi Cai and Donald C. Wunsch. "Counterexample of a Claim Pertaining to the Synthesis of a Recurrent Neural Network" Proceedings of the 2002 International Joint Conference on Neural Networks, 2002. IJCNN '02 (2002) Available at: http://works.bepress.com/donald-wunsch/187/