Neural Networks Activities at Thomson-CSF

  • F. Vallet
Chapter

Abstract

Thomson-CSF is strongly involved in the domain of neural networks [1,2,3,4]. The reason of this commitment is the potential capabilities of neural networks for discrimination and classification tasks, numeric-symbolic interfaces, signal and image processing, optimisation and data fusion. These capabilities are important for several equipments developed in the company (radar, sonar, telecommunication, IR/visible/radar image processors, simulators, video equipments), as well as for systems (air traffic control, weapon systems, telecommunication networks, battlefield management).

Keywords

Boolean Function Video Equipment Laboratoire Central Europhysics Letter Liquid Crystal Light Valve 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in to check access

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    B. Angéniol. Les réseaux neuro-mimétiques: de la recherche à l’industrie. Proceedings of the international workshop Neuro-NIMES 88 (Nimes, France, nov.88), p. 17, 1988.Google Scholar
  2. [2]
    B. Angéniol. Thomson-CSF strategy in Neural Networks. Conférence: Neural Computing, Commercial Prospects (Londre 16–17/2/89). Google Scholar
  3. [3]
    D. Potier and B. Angéniol. Activités de Thomson-CSF en Réseaux de Neurones. Bulletin de Liaison de la Recherche en Automatique et Informatique, Inria, 1989.Google Scholar
  4. [4]
    B. Angeniol F.vallet. Thomson-CSF: activities in Neural Networks. Conférence: Neural Computing, Commercial Prospects (Londre 15–16/2/90). Google Scholar
  5. [5]
    M. De Bollivier, A. Lemer, and J. Tanguy. Reconnaissance de bruits sous-marins par réseaux multicouches. Proceedings of the international workshop Neuro-NIMES 88 (Nimes,France,nov.88), pp. 423–430, 1988.Google Scholar
  6. [6]
    Y. Ammirati and D. Neveu. Classification de signaux sonar en mode actif. Proceeding of GRETSI 89 (12ème colloque, Juan-les-Pins, 12–16/6/89), pp. 391–394.Google Scholar
  7. [7]
    A. Lemer, JM. Nicolas, and P. Giancone. Identification automatique de bruits impulsifs sous-marins. Proceedings of GRETSI,1989,pp. 403–406, 1989.Google Scholar
  8. [8]
    JM. Nicolas, A. Lemer, and D. Legitimus. Identification automatique de bruits impulsifs en acoustique sous-marine par réseaux multicouche. Proceedings of the international workshop Neuro-NIMES 89 (Nimes,France,18–16/11/89)pp .269–278, 1989.Google Scholar
  9. [9]
    J. Loncelle. Détection de contours par rétro-propagation de gradient. Proceedings of the international workshop Neuro-NIMES 89 (Nimes,France,nov.89) pp.373–393, 1989.Google Scholar
  10. [10]
    F. Grizard and M. Revol. Application d’une méthode de recuit simulé à l’implantation de traitements sonar. To appear in proceedings of GRETSI 89. Google Scholar
  11. [11]
    J.-G. Cailton, B. Angéniol, and E. Marcadé. Constrained Back-propagation. Abstracts of the First Annual INNS Meeting, p. 539, 1988.Google Scholar
  12. [12]
    Ph. Réfrégier and J-M. Vignolle. An improved version of the pseudo-inverse solution for classification and neurl networks. Europhysics Letters, 10 (4):pp. 387–392, 1989.CrossRefGoogle Scholar
  13. [13]
    F Vallet. The Hebb rule for learning linearly separable functions: learning and generalisation. Europhysics Letters, 8 (8):pp. 747–751, 1989.CrossRefGoogle Scholar
  14. [14]
    F. Vallet, J-G. Cailton, and Ph. Réfrégier. Linear and nonlinear extension of the pseudo-inverse solution for learning boolean functions. Europhysics Letters, 9 (4):pp. 315–320, 1989.CrossRefGoogle Scholar
  15. [15]
    F. Vallet and J-G. Cailton. Recognition rates of the Hebb rule for learning boolean functions. 1990. To appear in Physical Review A.Google Scholar
  16. [16]
    F. Vallet, J-G. Cailton, and Ph. Réfrégier. Solving the problem of overfitting of the pseudoinverse solution for classification learning. 1989. International joint conference on neural networks, Washington D.C., June 18–22 (1989), vol.Il, p. 443–450.Google Scholar
  17. [17]
    F. Vallet. Optimization of the number of hidden cells in a mutilayer perceptron. Validation in the linear case. Proceedings of the workshop NATO ARW (february 89, Les Arcs), 1989.Google Scholar
  18. [18]
    B. Angéniol, G. de La Croix Vaubois, and J.Y. Le Texier. Self-Organizing feature maps and the travelling salesman problem. Neural networks, vol 1:pp. 289–293, 1988.CrossRefGoogle Scholar
  19. [19]
    P. Goyoneix. Self-organization and an optimization problem. Proceedings of the international workshop Neuro-NIMES 88 (Nimes, France, nov.88), pp. 149.Google Scholar
  20. [20]
    P. Comon. Séparation de mélanges de signaux. To appear in proceedings of GRETSI 89 (12ème colloque, Juan-les-Pins, 12–16/6/89), 1989.Google Scholar
  21. [21]
    P. Comon. Séparation of stochastic processes whose a linear mixture is observed. ONRNSFIEEE, Workshop on higher order spectral analysis, Vail (28–90/6/89). Google Scholar
  22. [22]
    B. Angéniol. Extraction of prototypes. Proceedings of the workshop NATO ARW (février 89, Les Arcs). Google Scholar
  23. [23]
    M. Mougeot, R. Azencott, and B. Angéniol. Compression d’images, réduction de données et rétropropagation. Communication in euro-image 88 (octobre 1988). Google Scholar
  24. [24]
    M. Mougeot, R. Azencott, and B. Angéniol. A study of image compression with backpropagation. Proceedings of the workshop NATO ARW (february 89, Les Arcs). Google Scholar
  25. [25]
    B. Derot, Ph. Escande, and C. Moulinoux. NACRE: A neuron-oriented programming environment. Proceedings of the international workshop Neuro-NIMES 89 (Nimes,France,1816/11/89), pp. 183–200, 1989.Google Scholar
  26. [26]
    C. Moulinoux, B. Derot, and G. de La Croix Vaubois. A high level language for neural networks specification. Proceedings of the workshop NATO ARW (february 89,Les Arcs). Google Scholar
  27. [27]
    C. Ernoult. Performance of backpropagation on a parallel transputer-based machine. Proceedings of the international workshop Neuro-NIMES 88 (Nimes, France, nov.88) p. 311.Google Scholar
  28. [28]
    Ph. Réfrégier. Phase optimisation of sdf filters. International symposium: Optics in computing, 1:p. 15, 1989.Google Scholar
  29. [29]
    Ph. Réfrégier and JP. Huignard. Multi criteria optimization approach for sdf filters. To appear in proceedings of the International topical meeting on Optical computing (Japan 1990 ).Google Scholar
  30. [30]
    B. Loiseaux, G. Illiaquer, and JP. Huignard. Dynamic optical cross-correlator using a liquid crystal light valve and a bso crystal in the fourier plane. Optical engineering, 24(1), 1985.Google Scholar

Copyright information

© Springer Science+Business Media Dordrecht 1990

Authors and Affiliations

  • F. Vallet
    • 1
  1. 1.Laboratoire Central de RecherchesThomson-CSFOrsay (cedex)France

Personalised recommendations