Abstract
Inspired by advances in evolutionary biology we extended existing evolutionary computation techniques and developed a self-organising, self-adaptable cellular system for multitask learning, called Evolvable Virtual Machine (EVM). The system comprises a specialised program architecture for referencing and addressing computational units (programs) and an infrastructure for executing those computational units within a global networked computing environment, such as Internet. Each program can be considered to be an agent and is capable of calling (co-operating with) other programs. In this system, complex relationships between agents may self-assemble in a symbiotic-like fashion. In this article we present an extension of previous work on the single threaded, single machine EVM architecture for use in global distributed environments. This paper presents a description of the extended Evolvable Virtual Machine (EVM) computational model, that can work in a global networked environment and provides the architecture for asynchronous massively parallel processing. The new computational environment is presented and followed with a discussion of experimental results.
This is a preview of subscription content, log in via an institution to check access.
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
Nowostawski, M., Epiney, L., Purvis, M.: Self-Adaptation and Dynamic Environment Experiments with Evolvable Virtual Machines. In: Brueckner, S.A., Serugendo, G.D.M., Hales, D., Zambonelli, F. (eds.) ESOA 2005. LNAI (LNCS), vol. 3910, pp. 46–60. Springer, Berlin Heidelberg New York (2006)
Bush, V.: As we may think. The Atlantic Monthly (1945), http://www.theatlantic.com/doc/194507/bush
Nelson, T.H.: A file structure for the complex, the changing and the indeterminate. In: Proceedings of the ACM 20th National Conference, Cleveland, OH, pp. 84–100. ACM Press, New York (1965)
Nowostawski, M., Purvis, M., Cranefield, S.: An architecture for self-organising Evolvable Virtual Machines. In: Brueckner, S.A., Serugendo, G.D.M., Karageorgos, A., Nagpal, R. (eds.) Engineering Self-Organising Systems. LNCS (LNAI), vol. 3464, Springer, Heidelberg (2005)
Eigen, M., Schuster, P.: The Hypercycle: A Principle of Natural Self-Organization. Springer, Heidelberg (1979)
Wright, S.: Evolution in mendelian populations. Genetics 16(3), 97–159 (1931)
Margulis, L.: Origin of Eukaryotic Cells. University Press, New Haven (1970)
Margulis, L.: Symbiosis in Cell Evolution. Freeman & Co., San Francisco (1981)
Mereschkowsky, K.S.: Über Natur und Ursprung der Chromatophoren im Pflanzenreiche. Biol. Zentralbl. 25, 593–604 (1905)
Wallin, I.: Symbionticism and the Origin of Species. Williams&Wilkins, Baltimore (1927)
Gupta, R.S., Golding, G.B.: The origin of the eukaryotic cell. Trends in Biochemical Sciences 21(10), 166–171 (1996)
Margulis, L., Sagan, D.: Microcosmos: Four Billion Years of Evolution from Our Microbial Ancestors. Summit Books, New York (1986)
Bray, D.A., Lewis, J., Raff, M., Roberts, K., Watson, J.D.: Molecular biology of the cell, 3rd edn. Garland Publishing, New York (1994)
Schmidhuber, J.: A general method for incremental self-improvement and multiagent learning. In: Yao, X. (ed.) Evolutionary Computation: Theory and Applications, pp. 81–123. Scientific Publishers Co., Singapore (1999)
Vose, M.D.: The Simple Genetic Algorithm: Foundations and Theory. In: A Bradford Book, MIT Press, Cambridge (1999)
Kugel, P.: Thinking may be more than computing. Cognition 18, 128–149 (1986)
Sipper, M.: The emergence of cellular computing, vol. 32(7), pp. 18–26. IEEE Computer, Los Alamitos (1999)
Wolfram, S.: Universality and complexity in cellular automata. Physica D 10, 1–35 (1984)
Teuscher, C.: Information processing in cells and tissues. BioSystems 76, 3–5 (2004)
Bonabeau, E., Dorigo, M., Theraulaz, G.: Swarm Intelligence: From Natural to Artificial Systems. Oxford University Press, Oxford (2000)
Schmidhuber, J.: Environment-independent reinforcement acceleration. Technical Note IDSIA-59-95, IDSIA, Lugano (1995)
Baxter, J.: A model of inductive bias learning. Journal of Artificial Intelligence Research 12, 149–198 (2000)
Caruana, R.: Multitask learning. In: Machine Learning, vol. 28, pp. 41–75. Kluwer Academic Publishers, Dordrecht (1997)
Thrun, S.: Is learning the n-th thing any easier than learning the first? In: Touretzky, D., Mozer, M. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 640–646. MIT Press, Cambridge (1996)
Thom, R.: Structural stability and morphogenesis. Addison Wesley, New York (1975)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Nowostawski, M., Purvis, M. (2007). Evolution and Hypercomputing in Global Distributed Evolvable Virtual Machines Environment. In: Brueckner, S.A., Hassas, S., Jelasity, M., Yamins, D. (eds) Engineering Self-Organising Systems. ESOA 2006. Lecture Notes in Computer Science(), vol 4335. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69868-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-69868-5_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69867-8
Online ISBN: 978-3-540-69868-5
eBook Packages: Computer ScienceComputer Science (R0)