Abstract
Although for reasons that are discussed, immunology have had a weak influence so far on the Ensign of artifacts, one key aspects 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 selfassertion role while being in constant shifting according to the organic"s ontogenic changes and in response to the environmental coupling. We argue that the Envelopment of complex systems, adaptive both at a structural and parametric levels, should comply with the following basic operational principles: - the structural adjustments intermittently occur following a longer time scale than the parametric adjustment - the structural plasticity amounts to the addition of new elements in the system and the suppression of redundant elements from it - the structural adjustments are EnpenEnnt on the temporal evolution of the internal parameters being subject to some learning i.e. when and how to perform a structural change should Enpend on data related to the dynamics of the parametric change so that the network endogenous behaviour and no exogenous criteria will guiEn these structural changes - these structural alterations have to be done in a “collective” spirit namely by applying heurisitics like “help the weakest elements (or compensate for them)”, “maintain diversity”, “fill the blank spaces”, “suppress redundant elements”. Three applications are briefly discussed: neural network classification, autonomous agent learning by reinforcement learnig and the control of chaos, where these principles are in full play and seem to have positive effect.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Barto, A. (1990), Connectionist Learning for Control. In Neural Networks for Control (Thomas Miller III, Richard Sutton and Paul Werbos eds.) MIT Press, pp 5–58.
Barto, A. and Singh, S.P. (1990), Reinforcement Learning and dynamic programming. In Proceedings of the Sixth Yale Workshop on Adaptive and Learning Systems, New Haven, CT., K.S. Narendra (Ed).
Bersini, H. and F. Varela (1990),Hints for adaptive problem solving gleaned from immune networks. In Proceedings of the first conference on Parallel Problem Solving from Nature - Schwefel and Miinner (Eds) - Springer Verlag. Pp 343‐354.
Bersini H., (1993), Immune Network and Adaptive Control. Toward a Practice of Autonomous Systems, In Proceedings of the First ECAL, Varela and Bourgine (Eds.), 217–225, MIT Press.
Bersini, H. (1992a), Reinforcement and Recruitment Learning for Adaptive Process Control- In Proceedings of the 1992 IFAC/IFIP/IMACS on Artificial Intelligence in Real Time Control pp.331–337.
Bersini, H. (1992b)The Interplay between the Dynamics and the Metadynamics of the Immune Network, Presented in the Third Conference on Artificial Life - Santa Fe 15-19 June.
Bersini H. and Varela F., (1994), The Immune Learning Mechanisms: Recruitment Reinforcement and their applications, In Computing with Biological Metaphors, R. Patton (Ed.), Chapman and Hall.
Booker, L.B, Goldberg, D.E. and J.H. Holland(1989) Classifier systems and genetic algorithms, Artificial Intelligence 40, Elsevier Science Publishers B.V. (North Holland) pp 235–282.
Dasgupta, D. and N. Attoh-Okine. (1996) Immunity-Based Systems: A Survey, Presented at the ICMAS workshop on Immunity-Based Systems, Japan (Enc"96).
En Boer, R.J. and A. Perelson. (1991),Size and Connectivity as Emergent Properties of a Enveloping Immune Network, InJ. Theoretical Biology, Vol. 149, pp. 381–424.
Enffuant, G. 1992, Reseaux Connectionistes Auto-Construits - These D"Etat.
Entours, V., Bersini, H., Stewart, J. and F. Varela(1994), Envelopment of an Idiotypic Network in Shape Space - inJournal of Theoretical Biology, Vol. 170, pp. 401–414.
Dorigo, M. and Bersini, H.(1994), A Comparative Analysis of Q-Iearning and Classifier Systems, In proceedings of SAB 94, MIT Press., pp. 248–255.
A.Duchateau,, N.H.H.BradshawandBersini1997, A Multi-Model Solution for the Control of Chaos, Submitted to International Journal of Control.
Fahlman S. and C. Lebiere(1990), The CascaEn-Correlation Learning Architecture, Advances in Neural Information Processing System, Vol 2, P.P. Morgan Kaufman Publishers, pp 524 – 532.
Farmer, D. (1991) A Rosetta Stone to Connectionism. In Emergent Computation, Forrest S. (Ed). MIT Press.
Fombellida M. (1992),MethoEns heuristiques et methoEns d"optimalisation non contraintes pour l"apprentissage Ens perceptrons multicouches, Proceedings of the fifth Int"l Conf. on Neural Networks & their application: Neuro-Nimes, pp 349–366.
Forrest, S., Hofmeyr, S.A., Somayaji, A. and T.A. Longstaff. (1996). A sense of self for unix processes. In Proceedings of IEEE Symposium on Research in Security and Privacy, Oakland, CA.
Goldberg, D.E. (1989), Genetic Algorithms in search, optimization and machine learning. Addison-Wesley Publishing Company, Inc.
Hirose Y., Yamashita K. and Hijiya S. (1991), Back-propagation Algorithm Which Varies the Number of Units, Neural Networks, Vol 4, pp 61–66.
Holland, J.H., Holyoak, K.J., Nisbett, R.E. & Thagard, P.R. (1986) Induction: Processes of inference, learning and discovery. Cambridge: MIT Press.
Jerne, N. (1974),Ann. Inst. Pasteur Immunol. 125C, pp. 435–441.
Kephart, J.O. (1994),A biologically inspired immune system for computer. In Proceedings of Artificial Life - MIT Press.
Lin L-J., (1992), Self-improving reactive agents based on reinforcement learning, planning and teaching. Machine Learning, 8, 3-4, 293–322.
Lundkvist, I., Coutinho, A. , Varela, F. and D. Holmberg(1989)EviEnnce for a functional idiotypic network among natural antibodies in normal mice, InProc. Natl. Acad. Sci. USA, Vol. 86, pp. 5074–5078.
MahaEnvan, S. and J. Connel (1992),Automatic programming of behaviorbased robots using reinforcement learning, In Artificial Intelligence 55, Elsevier Science Publishers B.V. (North Holland) pp.311–365.
Miller G., Todd P. and Hedge S. (1989),Ensigning Neural Networks using Genetic Algorithms, In Proceedings of the third Int"l Conf on Genetic Algorithms, pp 379–384.
Munos R, Patinel J. and Goyeau P., 1994. Partitioned Q-learning. CEMAGREF Technical Report, Paris, France - In proceedings of SAB 94 Conference, MIT Press, pp. 354–363.
Ott, E., Gerbogi, C. and J.A. Yorke. (1990), Controlling Chaos, Phys. Review Lett. 64(1196)292–295.
Perelson, A.S. (1988) Towards a Realistic Model of the Immune System, In Theoretical Immunology, Part Two, edited by A.S. Perelson. SFI Studies in the Sciences of Complexity, vol. 3, Reading, MA: Addison-Wesley, pp 377–401.
Perelson, A.S. (1990), Theoretical Immunology, In Lectures in Complex Systems - SFI Studies in the Sciences of Complexity, Lect. Vol. II, Edited by Erica Jen, Addison-Wesley, pp 465–500.
Salome, T. and H. Bersini. 1994. An Algorithm for Self-Structuring Neural Net Classifiers- In proceedings of the Second IEEE Conf. On Neural Network - ICNN"94 pp. 1307–1312.
Sutton, RS. (1990) Reinforcement Learning Architectures for Animats. In Proceedings of the First SAB Conference - Meyer and Wilson (Eds.) - MIT Press. pp.288–296.
Tsitsiklis J.N, (1993),Asynchronous Stochastic Approximation and Q-learning. Internal Report from Laboratory for Information and Encision Systems and the Operations Research Center, MIT.
Varela, F., A. Coutinho, B. Dupire and N. Vaz.(1988)Cognitive networks: Immune, neural and otherwise, In A. Perelson(Ed.), Theoretical Immunology, Vol.2SFI Series on the Science of Complexity, Addisson Wesley, New Jerseypp 359–375.
Varela, F., V. Sanchez and A. Coutinho (1989), Adaptive strategies gleaned from immune networks, In B. GoodwIn and P. Saunders (Eds.), Evolutionary and epigenetic order from complex systems: A Waddington Memorial Volume. Edinburgh U. Press.
Varela, F.J. and A. Coutinho.(1991), Second Generation Immune Network - inImmunology Today, Vol. 12 No 5.- pp.159–166.
Watkins C.J.C.H., (1989),Learning with Enlayed rewards. Ph. D. dissertation, Psychology Enpartment, University of Cambridge, England.
Watkins C.J.C.H. and Dayan P., (1992), Technical Note: Q-learning. Machine Learning, 8, 3–4, 279–292.
Weisbuch, G. , En Boer, RJ. and A.S. Perselson. (1990),Localized memories in idiotypic networks, J. Theor. BioI. 146 - pp. 483–499.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin HeiEnlberg
About this chapter
Cite this chapter
Bersini, H. (1993). The Endogenous Double Plasticity of the Immune Network and the Inspiration to be Drawn for Engineering Artifacts. In: Dasgupta, D. (eds) Artificial Immune Systems and Their Applications. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-59901-9_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-59901-9_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-64174-9
Online ISBN: 978-3-642-59901-9
eBook Packages: Springer Book Archive