Skip to main content
SpringerLink
Log in

Evolving Connectionist Machines — Framework, Biological Motivation and Implementation Issues

  • Chapter
Evolving Connectionist Systems

Part of the book series: Perspectives in Neural Computing ((PERSPECT.NEURAL))

  • 323 Accesses

Abstract

Chapters 2–6 presented different methods for creating evolving connectionist systems. This chapter presents a multi-agent implementation framework for building evolving connectionist machines that integrate several evolving connectionist systems together to solve a given task. The modules, as well as their internal structures, evolve in time. This chapter also discusses implementation issues of highly parallel evolving connectionist architectures — evolvable hardware. The chapter covers the following topics:

  • A framework for evolving connectionist machines

  • Biological motivation for ECOS — the “instinct” for information

  • Spatial and temporal complexity of ECOS

  • On-line feature selection and feature evaluation

  • An agent-based framework for evolving connectionist machines

  • Evolving hardware

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 74.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Further Reading

  • Kasabov, N. (1998a) ECOS–A framework for evolving connectionist systems and the “eco” training method. In Proceedings of ICONIP’98–The Fifth International Conference on Neural Information Processing, Vol. 3 (eds. S. Usui and T. Omori ), Kitakyushu, Japan. IOS Press, pp. 1232–1235.

    Google Scholar 

  • Kasabov, N. (1998b) Evolving fuzzy neural networks–algorithms, applications and biological motivation. In Methodologies for the Conception, Design and Application of Soft Computing (eds. T. Yamakawa and G. Matsumoto ). World Scientific, Singapore, pp. 271–274.

    Google Scholar 

  • Kasabov, N. (1998c) Evolving fuzzy neural networks: theory and Applications for on-line adaptive prediction, decision making and control. Australian Journal of Intelligent Information Processing Systems, 5 (3), 154–160.

    Google Scholar 

  • Kasabov, N. (1998d) The ECOS framework and the ECO learning method for evolving connectionist systems. Journal of Advanced Computational Intelligence, 2 (6), 195–202.

    Google Scholar 

  • Kasabov, N. (2001a) Brain-like functions in evolving connectionist systems or on-line, knowledge based learning. In What Should Be Computed to Understand and Model Brain Functions (ed. T. Kitamura ). World Scientific, Singapore, pp. 77–113.

    Google Scholar 

  • Kasabov, N. (2001b) On-line learning, reasoning, rule extraction and aggregation in locally optimised evolving fuzzy neural networks. Neurocomputing, 41 (1–4), 25–45.

    Article  MATH  Google Scholar 

  • Kasabov, N. (2001c) Evolving fuzzy neural network for supervised/unsupervised knowledge-based learning. IEEE Transactions on Man, Machine and Cybernetics, 31 (6), 902–918.

    Article  Google Scholar 

  • Kasabov, N. (2001d) Adaptive learning system and method. Patent No. PCT WO 01/78003 Al.

    Google Scholar 

  • Amit, D. (1989) Modeling Brain Function: The World ofAttractorNeural Networks. Cambridge University Press, Cambridge.

    Book  Google Scholar 

  • Arbib, M. (1972) The Metaphorical Brain - An Introduction to Cybernetics as Artificial Intelligence and Brain Theory. Wiley Interscience, New York.

    MATH  Google Scholar 

  • Arbib, M. (1987) Brains, Machines and Mathematics. Springer-Verlag, Berlin.

    Book  MATH  Google Scholar 

  • Arbib, M. (1998) From vision to action via distributed computation. In Brain-Like Computing and Intelligent Information Systems (eds. S. Amari and N. Kasabov ). Springer-Verlag, Singapore and Heidelberg.

    Google Scholar 

  • Churchland, P. and Sejnowski, T. (1992) The Computational Brain. MIT Press, Cambridge, MA.

    Google Scholar 

  • Deacon, T. (1988) Human brain evolution: evolution of language circuits. In NATO ASI Series Intelligence and Evolutionary Biology (eds. H. Jerison and 1. Jerison). Springer-Verlag, Berlin.

    Google Scholar 

  • Deacon, T. (1998) The Symbolic Species. The Co-evolution of Language and the Human Brain. Penguin, London.

    Google Scholar 

  • Freeman, W. (2001) How Brains Make Up Their Minds. Columbia University Press, New York.

    Google Scholar 

  • Grossberg, S. (1982) Studies of Mind and Brain. Reidel, Boston.

    Book  MATH  Google Scholar 

  • Joseph, S. R. H. (1998) Theories of adaptive neural growth. PhD Thesis, University of Edinburgh.

    Google Scholar 

  • Taylor, J. G. (1998) Neural networks for consciousness. In Brain-Like Computing and Intelligent Information Systems (eds. S. Amari and N. Kasabov ). Springer-Verlag, Singapore and Heidelberg.

    Google Scholar 

  • Taylor, J. G. (1999) The Race for Consciousness. MIT Press, Cambridge, MA.

    Google Scholar 

  • Van Owen, A. (1994) Activity-dependent neural network development. Network Computation in Neural Systems, 5, 401–423.

    Article  Google Scholar 

  • Wong, R. O. L. (1995) Use, disuse, and growth of the brain. Proceedings of the National Academy of Sciences USA, 92 (6), 1797–1799.

    Article  Google Scholar 

  • Durand, G., Kovalchuk, Y. and Konnerth, A. (1996) Long-term potentiation and functional synapse induction in developing hippocampus. Nature, 381 (5), 71–75.

    Article  Google Scholar 

  • Eriksson, P. S., Perfilieva, E., Bjork-Eriksson, T., Alborn, A. M., Norborg, C., Peterson, D. A. and Gag, F. H. (1998) Neurogenesis in the adult human hippocampus. Nature Medicine, 4, 1313–1317.

    Article  Google Scholar 

  • Grossberg, S. and Merrill, J. W. L. (1996) The hippocampus and cerebellum in adaptively timed learning,. recognition and movement. Journal of Cognitive Neuroscience, 8, 257–277.

    Article  Google Scholar 

  • McClelland, J., McNaughton, B. and O’Reilly, R. (1995) Why are there complementary learning systems in the hippocampus and neocortex? Insights from the success and failure of connectionist models of learning and memory. Psychological Review, 102, 419–457.

    Article  Google Scholar 

  • Kasabov, N. (2001a) Brain-like functions in evolving connectionist systems or on-line, knowledge based learning. In What Should Be Computed to Understand and Model Brain Functions (ed. T. Kitamura ). World Scientific, Singapore, pp. 77–113.

    Google Scholar 

  • Kitamura, T. (ed.) (2001) What Should Be Computed to Understand and Model Brain Functions? World Scientific, Singapore.

    Google Scholar 

  • West, M. and Harrison, P. J. (1989) Bayesian Forecasting and Dynamic Models. Springer-Verlag, New York.

    MATH  Google Scholar 

  • Adami, C. (1998) Introduction to Artificial Life. Springer-Verlag, London.

    Book  MATH  Google Scholar 

  • Stephens, C., Olmedo, I., Vargas, J. and Waelbroack, H. (2000), Self adaptation in evolving systems. Artificial Life, 4 (2), 183–201.

    Article  Google Scholar 

  • Woldrige, M. and Jennings, N. (1995) Intelligent agents: theory and practice. The Knowledge Engineering Review, 10.

    Google Scholar 

  • Nolfi, S. and Floreano, D. (2000) Evolutionary Robotics. MIT Press, Cambridge, MA.

    Google Scholar 

  • Jordan, M. and Jacobs, R. (1994) Hierarchical mixtures of experts and the EM algorithm. Neural Computation, 6, 181–214.

    Article  Google Scholar 

  • de Bollivier, M., Gallinari, P. and Thiria, S. (1990) Cooperation of neural nets for robust classification. Université de Paris-Sud, Report 547, Informatiques.

    Google Scholar 

  • Glarkson, T., Goarse, D. and Taylor, J. (1992) From wetware to hardware: reverse engineering using probabilistic RAMs. Journal of Intelligent Systems, 2, 11–30.

    Google Scholar 

  • Zamir, B. (1983) Introduction to The Theory of Automata. Reston Publishing Company, Reston, VA. ZISC Manual (2001) Zero Instruction Set Computer. Silicon Recognition, Inc.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of Otago, Dunedin, New Zealand

    Nikola Kasabov PhD, MSc, FRSNZ (Director of Knowledge Engineering and Discovery Research Institute)

  2. Auckland University of Technology, New Zealand

    Nikola Kasabov PhD, MSc, FRSNZ (Director of Knowledge Engineering and Discovery Research Institute)

Authors
  1. Nikola Kasabov PhD, MSc, FRSNZ
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

Copyright information

© 2003 Springer-Verlag London

About this chapter

Cite this chapter

Kasabov, N. (2003). Evolving Connectionist Machines — Framework, Biological Motivation and Implementation Issues. In: Evolving Connectionist Systems. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-3740-5_7

Download citation

  • DOI: https://doi.org/10.1007/978-1-4471-3740-5_7

  • Publisher Name: Springer, London

  • Print ISBN: 978-1-85233-400-0

  • Online ISBN: 978-1-4471-3740-5

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation