Although for reasons that are discussed, immunology have had a weak influence so far on the design of artifacts, one key aspect of immune networks, namely their endogenous double plasticity could be of interest for future engineering applications facing complex, hard to model and time-varying environments. In immune networks, this double plasticity allows the system to conduct its self-assertion role while being in constant shifting according to the organism’s ontogenic changes and in response to the environmental coupling.


Chaotic System Synaptic Weight Complex Adaptive System Structural Plasticity Immune Network 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Barto, A. (1990). Connectionist learning for control. In T. Miller III, R. Sutton, & Paul Werbos (eds.), Neural networks for control (pp. 5–58). Cambridge, MA: MIT Press.Google Scholar
  2. Barto, A., & S.P. Singh (1990). Reinforcement Learning and dynamic programming. In K.S. Narendra (ed.), Proceedings of the Sixth Yale Workshop on Adaptive and Learning Systems (248–256). New Haven, CT: IFAC.Google Scholar
  3. Bersini, H. (1992a). Reinforcement and recruitment learning for adaptive process control. Proceedings of the 1992 IFAC/IFIP/IMACS on Artificial Intelligence in Real Time Control (pp. 331–337). Delft, The Netherlands: Delft University of Technology.Google Scholar
  4. Bersini, H. (1992b). The interplay between the dynamics and the metadynamics of the immune network. Presented at the Third Conference on Artificial Life (15–19 June). Santa Fe, NM: Addison-Wesley.Google Scholar
  5. Bersini, H. (1993). Immune network and adaptive control. Toward a practice of autonomous systems. In F.J. Varela & P. Bourgine (eds.), Proceedings of the First European Conference on Artificial Life (pp. 217–225). Cambridge, MA: MIT Press.Google Scholar
  6. Bersini, H., & F. Varela (1990). Hints for adaptive problem solving gleaned from immune networks. In H.P. Schwefel & R. Männer (eds.), Proceedings of the first conference on parallel problem solving from nature (pp. 343–354). Heidelberg, Germany: Springer Verlag.Google Scholar
  7. Bersini, H., & F. Varela (1994). The immune learning mechanisms: Recruitment reinforcement and their applications. In R. Patton (ed.), Computing with biological metaphors (166–192). London: Chapman and Hall.Google Scholar
  8. Booker, L.B., D.E. Goldberg, & J.H. Holland (1989). Classifier systems and genetic algorithms. Artificial Intelligence 40, 235–282.CrossRefGoogle Scholar
  9. Dasgupta, D., & N. Attoh-Okine (1997). Immunity-based systems: A Survey. Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (pp. 363–374). Orlando, FA (October 12–15).Google Scholar
  10. De Boer, R.J., & A. Perelson (1991). Size and connectivity as emergent properties of a developing immune network. Journal of Theoretical Biology 149, 381–424.CrossRefGoogle Scholar
  11. Deffuant, G. (1992). Reseaux connectionistes auto-construits. These d’Etat. Université the Paris.Google Scholar
  12. Detours, V., H. Bersini, J. Stewart, & F. Varela (1994). Development of an idiotypic network in shape space. Journal of Theoretical Biology 170, 401–414.CrossRefGoogle Scholar
  13. Dorigo, M., & H. Bersini (1994). A comparative analysis of Q-learning and classifier systems. Proceedings of Simulation of Adaptive Behaviour (pp. 248–255). Cambridge, MA: MIT Press.Google Scholar
  14. Duchateau, A., N. Bradshaw, & H. Bersini (1997). A multi-model solution for the control of chaos. Submitted to International Journal of Control.Google Scholar
  15. Fahlman S., & C. Lebiere (1990).The cascade-correlation learning architecture. Advances in Neural Information Processing System, Vol 2 (pp. 524–532). San Mateo, CA: Morgan Kaufmann.Google Scholar
  16. Farmer, J.D. (1991). A Rosetta stone to connectionism. In S. Forrest (ed.), Emergent computation (124–146). Cambridge, MA: MIT Press.Google Scholar
  17. Fombellida, M. (1992). Méthodes heuristiques et méthodes d’optimalisation non contraintes pour l’apprentissage des perceptrons multicouches. Proceedings of the fifth International Conference on Neural Networks & their application (pp. 349–366). Nîmes, France: Neuro-Nîmes.Google Scholar
  18. Forrest, S., S.A. Hofineyr, A. Somayaji, & T.A. Longstaff (1996). A sense of self for Unix processes. Proceedings of IEEE Symposium on Research in Security and Privacy. Oakland, CA.Google Scholar
  19. Goldberg, D.E. (1989). Genetic algorithms in search, optimization and machine learning. Redwood City, CA: Addison-Wesley.MATHGoogle Scholar
  20. Hirose, Y., K. Yamashita, & S. Hijiya (1991). Back-propagation algorithm which varies the number of units. Neural Networks, Vol 4, 61–66.CrossRefGoogle Scholar
  21. Holland, J.H., K.J. Holyoak, R.E. Nisbett, & P.R. Thagard (1986), Induction: Processes of inference, learning and discovery. Cambridge, MA: MIT Press.Google Scholar
  22. Jerne, N. (1974). Towards a network theory of the immune system. Annales d’Immunologie de l’Institut Pasteur 125C, 373–389.Google Scholar
  23. Kephart, J.O. (1994). A biologically inspired immune system for computer. Proceedings of Artificial Life (130–139). Cambridge, MA: MIT Press.Google Scholar
  24. Lin, L.-J. (1992). Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning 8, 3–4, 293–322.Google Scholar
  25. Lundkvist, I., A. Coutinho, F. Varela, & D. Holmberg (1989). Evidence for a functional idiotypic network among natural antibodies in normal mice. Proceedings of the National Academy of Sciences, USA, Vol. 86 (pp. 5074–5078).CrossRefGoogle Scholar
  26. Mahadevan, S., & J.H. Connell (1992). Automatic programming of behavior-based robots using reinforcement learning. Artificial Intelligence 55, 311–365.CrossRefGoogle Scholar
  27. Miller G., P. Todd, & S. Hedge (1989). Designing neural networks using genetic algorithms. Proceedings of the third International Conference on Genetic Algorithms (pp. 379–384). San Diego, CA: Morgan Kaufman.Google Scholar
  28. Munos R., J. Patinel, & P. Goyeau (1994). Partitioned Q-learning. Proceedings of SAB 94 Conference (pp. 354–363). Cambridge, MA: MIT Press.Google Scholar
  29. Ott, E., C. Gerbogi, & J.A. Yorke (1990). Controlling chaos. Physical Review Letters 64(1196), 292–295.Google Scholar
  30. Perelson, A.S. (1988). Towards a realistic model of the immune system. In A.S. Perelson (ed.), Theoretical immunology. Part Two. SFI studies in the sciences of complexity, vol. 3 (pp. 377–401). Reading, MA: Addison-Wesley.Google Scholar
  31. Perelson, A.S. (1990). Theoretical immunology. In E. Jen (ed.), Lectures in complex systems. Studies in the sciences of complexity, Lect. Vol. II (pp. 465–500). Santa Fe, NM: Addison-Wesley.Google Scholar
  32. Salomé, T., & H. Bersini (1994). An algorithm for self-structuring neural net classifiers. Proceedings of the Second IEEE Conference on Neural Network — ICNN ′94 (pp. 1307–1312). Orlando, FA: IEEE Service Center.Google Scholar
  33. Sutton, R.S. (1990). Reinforcement learning architectures for animats. In J.-A. Meyer & S.W. Wilson (eds.), Proceedings of the First SAB Conference (pp. 288–296). Cambridge, MA: MIT Press.Google Scholar
  34. Tsitsiklis, J.N. (1993). Asynchronous stochastic approximation and Q-learning. Internal report from laboratory for information and decision systems and the operations research center. Cambridge, MA: MIT Press.Google Scholar
  35. Varela, F., A. Coutinho, B. Dupire, & N. Vaz (1988). Cognitive networks: Immune, neural and otherwise. In A. Perelson (ed.), Theoretical immunology. Vol 2 SFI Series on the Science of Complexity (pp. 359–375). Santa Fe, NM: Addison-Wesley.Google Scholar
  36. Varela, F., V. Sanchez, & A. Coutinho (1989). Adaptive strategies gleaned from immune networks. In B. Goodwin & P. Saunders (eds.), Evolutionary and epigenetic order from complex systems: A Waddington Memorial Volume. Edinburgh: Edinburgh University Press.Google Scholar
  37. Varela, F.J., & A. Coutinho (1991). Second generation immune network. Immunology Today 12(5), 159–166.Google Scholar
  38. Watkins, C.J.C.H. (1989). Learning with delayed rewards. PhD dissertation. Cambridge, England: University of Cambridge.Google Scholar
  39. Watkins C.J.C.H., & P. Dayan (1992). Technical note: Q-learning. Machine Learning 8, 3–4, 279–292.Google Scholar
  40. Weisbuch, G., R.J. De Boer, & A.S. Perelson (1990). Localized memories in idiotypic networks. Journal of Theoretical Biology 146, 483–499.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media Dordrecht 2000

Authors and Affiliations

  • Hugues Bersini
    • 1
  1. 1.Université Libre de BruxellesBelgium

Personalised recommendations