Application New Approach with Two Networks Slow and Fast on the Asynchronous Machine

In this paper, we propose a new modular approach called neuroglial consisting of two neural networks slow and fast which emulates a biological reality recently discovered. The implementation is based on complex multi-time scale systems; validation is performed on the model of the asynchronous machine. We applied the geometric approach based on the Gerschgorin circles for the decoupling of fast and slow variables, and the method of singular perturbations for the development of reductions models.

This new architecture allows for smaller networks with less complexity and better performance in terms of mean square error and convergence than the single network model.

• Samia Salah
• M’hamed Hadj Sadok
• Abderrezak Guessoum

• Gerschgorin’s Circles
• Neuroglial Network
• Multi time scales systems
• Singular perturbation method.

[1] “Astrocytes”, Science & Vie, n° 1045, p. 67, Nov 2005.
[2] P. Kokotovic, H.K. Khalil and J. O'reill, “Singular Perturbation
Methods in Control. Analysis and Design”, Academic Press London,
1968.
[3] O. Touhami, A. Mezouar, R. Ibtiouen and S.Mekhtoub, “Dynamics
Separation of Induction Machine Models Using Gerschgorin’s Circles
and Singular Perturbations”, IEEE-ICEEE 2004, Research Laborator of
Electrotechnic- Polytechnic National School.
[4] H. Guesbaoui and C. lung, “Multi time Scale Modelling in Electrical
Machines”, Centre de Recherche en Automatique de Nancy.
[5] E. Ronco, H. Gollee and P. Gawthrop , “ Modular neural networks and
self decomposition”, Technical Report CSC-96012, 11 Fev 1997.
[6] Happel1, M.J. Murre , “ The Design and Evolution of Modular Neural
Network Architectures”, Proceedings of the 1992 International
Conference on Artificial Neural Networks, 1994.
[7] I. Kirschning, H. Tomabechi and J.I. Aoe, “A Parallel Recurrent
Cascade-Correlation Neural Network with Natural Connectionist
Glue”, Proceedings of the IEEE ICNN, Perth, Australia 1995.
[8] M.P. Perrone and L.N. Cooper, “When networks disagree: Ensembles
methods for Hybrid neural networks”, Artificial neural networks for
speech and vision October 1992.